Sean Richardson

Mark Muchane, Sean Richardson, Kiho Park et al.

Sparse dictionary learning (and, in particular, sparse autoencoders) attempts to learn a set of human-understandable concepts that can explain variation on an abstract space. A basic limitation of this approach is that it neither exploits nor represents the semantic relationships between the learned concepts. In this paper, we introduce a modified SAE architecture that explicitly models a semantic hierarchy of concepts. Application of this architecture to the internal representations of large language models shows both that semantic hierarchy can be learned, and that doing so improves both reconstruction and interpretability. Additionally, the architecture leads to significant improvements in computational efficiency.

David Reber, Sean Richardson, Todd Nief et al.

Reward models are widely used as proxies for human preferences when aligning or evaluating LLMs. However, reward models are black boxes, and it is often unclear what, exactly, they are actually rewarding. In this paper we develop Rewrite-based Attribute Treatment Estimator (RATE) as an effective method for measuring the sensitivity of a reward model to high-level attributes of responses, such as sentiment, helpfulness, or complexity. Importantly, RATE measures the causal effect of an attribute on the reward. RATE uses LLMs to rewrite responses to produce imperfect counterfactuals examples that can be used to measure causal effects. A key challenge is that these rewrites are imperfect in a manner that can induce substantial bias in the estimated sensitivity of the reward model to the attribute. The core idea of RATE is to adjust for this imperfect-rewrite effect by rewriting twice. We establish the validity of the RATE procedure and show empirically that it is an effective estimator.

Todd Nief, David Reber, Sean Richardson et al.

When an LLM learns a new fact during finetuning (e.g., new movie releases, newly elected pope, etc.), where does this information go? Are entities enriched with relation information, or do models recall information just-in-time before a prediction? Or, are ``all of the above'' true with LLMs implementing multiple redundant heuristics? Existing localization approaches (e.g., activation patching) are ill-suited for this analysis because they usually \textit{replace} parts of the residual stream, thus overriding previous information. To fill this gap, we propose \emph{dynamic weight grafting}, a technique that selectively grafts weights from a finetuned model onto a pretrained model. Using this technique, we show two separate pathways for retrieving finetuned relation information: 1) ``enriching" the residual stream with relation information while processing the tokens that correspond to an entity (e.g., ``Zendaya'' in ``Zendaya co-starred with John David Washington'') and 2) ``recalling" this information at the final token position before generating a target fact. In some cases, models need information from both of these pathways to correctly generate finetuned facts while, in other cases, either the ``enrichment" or ``recall" pathway alone is sufficient. We localize the ``recall'' pathway to model components -- finding that ``recall" occurs via both task-specific attention mechanisms and an entity-specific extraction step in the feedforward networks of the final layers before the target prediction. By targeting model components and parameters, as opposed to just activations, we are able to understand the \textit{mechanisms} by which finetuned knowledge is retrieved during generation.