Wes Gurnee

Nikhil Garg, Wes Gurnee, David Rothschild et al.

Every representative democracy must specify a mechanism under which voters choose their representatives. The most common mechanism in the United States -- Winner takes all single-member districts -- both enables substantial partisan gerrymandering and constrains `fair' redistricting, preventing proportional representation in legislatures. We study the design of \textit{multi-member districts (MMDs)}, in which each district elects multiple representatives, potentially through a non-Winner takes all voting rule. We carry out large-scale empirical analyses for the U.S. House of Representatives under MMDs with different social choice functions, under algorithmically generated maps optimized for either partisan benefit or proportionality. Doing so requires efficiently incorporating predicted partisan outcomes -- under various multi-winner social choice functions -- into an algorithm that optimizes over an ensemble of maps. We find that with three-member districts using Single Transferable Vote, fairness-minded independent commissions would be able to achieve proportional outcomes in every state up to rounding, \textit{and} advantage-seeking partisans would have their power to gerrymander significantly curtailed. Simultaneously, such districts would preserve geographic cohesion. Through simulation, we find that the insights are robust to cross-party voting. In the process, we advance a rich research agenda at the intersection of social choice and computational gerrymandering.

Dimitris Bertsimas, Wes Gurnee

Discovering governing equations of complex dynamical systems directly from data is a central problem in scientific machine learning. In recent years, the sparse identification of nonlinear dynamics (SINDy) framework, powered by heuristic sparse regression methods, has become a dominant tool for learning parsimonious models. We propose an exact formulation of the SINDy problem using mixed-integer optimization (MIO) to solve the sparsity constrained regression problem to provable optimality in seconds. On a large number of canonical ordinary and partial differential equations, we illustrate the dramatic improvement of our approach in accurate model discovery while being more sample efficient, robust to noise, and flexible in accommodating physical constraints.

Zhonghao He, Jascha Achterberg, Katie Collins et al. · cambridge

As deep learning systems are scaled up to many billions of parameters, relating their internal structure to external behaviors becomes very challenging. Although daunting, this problem is not new: Neuroscientists and cognitive scientists have accumulated decades of experience analyzing a particularly complex system - the brain. In this work, we argue that interpreting both biological and artificial neural systems requires analyzing those systems at multiple levels of analysis, with different analytic tools for each level. We first lay out a joint grand challenge among scientists who study the brain and who study artificial neural networks: understanding how distributed neural mechanisms give rise to complex cognition and behavior. We then present a series of analytical tools that can be used to analyze biological and artificial neural systems, organizing those tools according to Marr's three levels of analysis: computation/behavior, algorithm/representation, and implementation. Overall, the multilevel interpretability framework provides a principled way to tackle neural system complexity; links structure, computation, and behavior; clarifies assumptions and research priorities at each level; and paves the way toward a unified effort for understanding intelligent systems, may they be biological or artificial.

Wes Gurnee, Max Tegmark

The capabilities of large language models (LLMs) have sparked debate over whether such systems just learn an enormous collection of superficial statistics or a set of more coherent and grounded representations that reflect the real world. We find evidence for the latter by analyzing the learned representations of three spatial datasets (world, US, NYC places) and three temporal datasets (historical figures, artworks, news headlines) in the Llama-2 family of models. We discover that LLMs learn linear representations of space and time across multiple scales. These representations are robust to prompting variations and unified across different entity types (e.g. cities and landmarks). In addition, we identify individual "space neurons" and "time neurons" that reliably encode spatial and temporal coordinates. While further investigation is needed, our results suggest modern LLMs learn rich spatiotemporal representations of the real world and possess basic ingredients of a world model.

Lucia Quirke, Lovis Heindrich, Wes Gurnee et al.

Prior work has shown the existence of contextual neurons in language models, including a neuron that activates on German text. We show that this neuron exists within a broader contextual n-gram circuit: we find late layer neurons which recognize and continue n-grams common in German text, but which only activate if the German neuron is active. We investigate the formation of this circuit throughout training and find that it is an example of what we call a second-order circuit. In particular, both the constituent n-gram circuits and the German detection circuit which culminates in the German neuron form with independent functions early in training - the German detection circuit partially through modeling German unigram statistics, and the n-grams by boosting appropriate completions. Only after both circuits have already formed do they fit together into a second-order circuit. Contrary to the hypotheses presented in prior work, we find that the contextual n-gram circuit forms gradually rather than in a sudden phase transition. We further present a range of anomalous observations such as a simultaneous phase transition in many tasks coinciding with the learning rate warm-up, and evidence that many context neurons form simultaneously early in training but are later unlearned.

Wes Gurnee, Emmanuel Ameisen, Isaac Kauvar et al.

Language models can perceive visual properties of text despite receiving only sequences of tokens-we mechanistically investigate how Claude 3.5 Haiku accomplishes one such task: linebreaking in fixed-width text. We find that character counts are represented on low-dimensional curved manifolds discretized by sparse feature families, analogous to biological place cells. Accurate predictions emerge from a sequence of geometric transformations: token lengths are accumulated into character count manifolds, attention heads twist these manifolds to estimate distance to the line boundary, and the decision to break the line is enabled by arranging estimates orthogonally to create a linear decision boundary. We validate our findings through causal interventions and discover visual illusions--character sequences that hijack the counting mechanism. Our work demonstrates the rich sensory processing of early layers, the intricacy of attention algorithms, and the importance of combining feature-based and geometric views of interpretability.

Andy Arditi, Oscar Obeso, Aaquib Syed et al.

Conversational large language models are fine-tuned for both instruction-following and safety, resulting in models that obey benign requests but refuse harmful ones. While this refusal behavior is widespread across chat models, its underlying mechanisms remain poorly understood. In this work, we show that refusal is mediated by a one-dimensional subspace, across 13 popular open-source chat models up to 72B parameters in size. Specifically, for each model, we find a single direction such that erasing this direction from the model's residual stream activations prevents it from refusing harmful instructions, while adding this direction elicits refusal on even harmless instructions. Leveraging this insight, we propose a novel white-box jailbreak method that surgically disables refusal with minimal effect on other capabilities. Finally, we mechanistically analyze how adversarial suffixes suppress propagation of the refusal-mediating direction. Our findings underscore the brittleness of current safety fine-tuning methods. More broadly, our work showcases how an understanding of model internals can be leveraged to develop practical methods for controlling model behavior.

Joshua Engels, Eric J. Michaud, Isaac Liao et al.

Recent work has proposed that language models perform computation by manipulating one-dimensional representations of concepts ("features") in activation space. In contrast, we explore whether some language model representations may be inherently multi-dimensional. We begin by developing a rigorous definition of irreducible multi-dimensional features based on whether they can be decomposed into either independent or non-co-occurring lower-dimensional features. Motivated by these definitions, we design a scalable method that uses sparse autoencoders to automatically find multi-dimensional features in GPT-2 and Mistral 7B. These auto-discovered features include strikingly interpretable examples, e.g. circular features representing days of the week and months of the year. We identify tasks where these exact circles are used to solve computational problems involving modular arithmetic in days of the week and months of the year. Next, we provide evidence that these circular features are indeed the fundamental unit of computation in these tasks with intervention experiments on Mistral 7B and Llama 3 8B, and we examine the continuity of the days of the week feature in Mistral 7B. Overall, our work argues that understanding multi-dimensional features is necessary to mechanistically decompose some model behaviors.

Wes Gurnee, Theo Horsley, Zifan Carl Guo et al.

A basic question within the emerging field of mechanistic interpretability is the degree to which neural networks learn the same underlying mechanisms. In other words, are neural mechanisms universal across different models? In this work, we study the universality of individual neurons across GPT2 models trained from different initial random seeds, motivated by the hypothesis that universal neurons are likely to be interpretable. In particular, we compute pairwise correlations of neuron activations over 100 million tokens for every neuron pair across five different seeds and find that 1-5\% of neurons are universal, that is, pairs of neurons which consistently activate on the same inputs. We then study these universal neurons in detail, finding that they usually have clear interpretations and taxonomize them into a small number of neuron families. We conclude by studying patterns in neuron weights to establish several universal functional roles of neurons in simple circuits: deactivating attention heads, changing the entropy of the next token distribution, and predicting the next token to (not) be within a particular set.

Nicholas Sofroniew, Isaac Kauvar, William Saunders et al.

Large language models (LLMs) sometimes appear to exhibit emotional reactions. We investigate why this is the case in Claude Sonnet 4.5 and explore implications for alignment-relevant behavior. We find internal representations of emotion concepts, which encode the broad concept of a particular emotion and generalize across contexts and behaviors it might be linked to. These representations track the operative emotion concept at a given token position in a conversation, activating in accordance with that emotion's relevance to processing the present context and predicting upcoming text. Our key finding is that these representations causally influence the LLM's outputs, including Claude's preferences and its rate of exhibiting misaligned behaviors such as reward hacking, blackmail, and sycophancy. We refer to this phenomenon as the LLM exhibiting functional emotions: patterns of expression and behavior modeled after humans under the influence of an emotion, which are mediated by underlying abstract representations of emotion concepts. Functional emotions may work quite differently from human emotions, and do not imply that LLMs have any subjective experience of emotions, but appear to be important for understanding the model's behavior.

Vedang Lad, Jin Hwa Lee, Wes Gurnee et al.

We investigate the robustness of Large Language Models (LLMs) to structural interventions by deleting and swapping adjacent layers during inference. Surprisingly, models retain 72-95% of their original top-1 prediction accuracy without any fine-tuning. We find that performance degradation is not uniform across layers: interventions to the early and final layers cause the most degradation, while the model is remarkably robust to dropping middle layers. This pattern of localized sensitivity motivates our hypothesis of four stages of inference, observed across diverse model families and sizes: (1) detokenization, where local context is integrated to lift raw token embeddings into higher-level representations; (2) feature engineering, where task- and entity-specific features are iteratively refined; (3) prediction ensembling, where hidden states are aggregated into plausible next-token predictions; and (4) residual sharpening, where irrelevant features are suppressed to finalize the output distribution. Synthesizing behavioral and mechanistic evidence, we provide a framework for interpreting depth-dependent computations in LLMs.

Alessandro Stolfo, Ben Wu, Wes Gurnee et al.

Despite their widespread use, the mechanisms by which large language models (LLMs) represent and regulate uncertainty in next-token predictions remain largely unexplored. This study investigates two critical components believed to influence this uncertainty: the recently discovered entropy neurons and a new set of components that we term token frequency neurons. Entropy neurons are characterized by an unusually high weight norm and influence the final layer normalization (LayerNorm) scale to effectively scale down the logits. Our work shows that entropy neurons operate by writing onto an unembedding null space, allowing them to impact the residual stream norm with minimal direct effect on the logits themselves. We observe the presence of entropy neurons across a range of models, up to 7 billion parameters. On the other hand, token frequency neurons, which we discover and describe here for the first time, boost or suppress each token's logit proportionally to its log frequency, thereby shifting the output distribution towards or away from the unigram distribution. Finally, we present a detailed case study where entropy neurons actively manage confidence in the setting of induction, i.e. detecting and continuing repeated subsequences.

Wes Gurnee, Neel Nanda, Matthew Pauly et al.

Despite rapid adoption and deployment of large language models (LLMs), the internal computations of these models remain opaque and poorly understood. In this work, we seek to understand how high-level human-interpretable features are represented within the internal neuron activations of LLMs. We train $k$-sparse linear classifiers (probes) on these internal activations to predict the presence of features in the input; by varying the value of $k$ we study the sparsity of learned representations and how this varies with model scale. With $k=1$, we localize individual neurons which are highly relevant for a particular feature, and perform a number of case studies to illustrate general properties of LLMs. In particular, we show that early layers make use of sparse combinations of neurons to represent many features in superposition, that middle layers have seemingly dedicated neurons to represent higher-level contextual features, and that increasing scale causes representational sparsity to increase on average, but there are multiple types of scaling dynamics. In all, we probe for over 100 unique features comprising 10 different categories in 7 different models spanning 70 million to 6.9 billion parameters.