I Predict Therefore I Am: Is Next Token Prediction Enough to Learn Human-Interpretable Concepts from Data?
This addresses the fundamental question of how LLMs capture meaning, with implications for interpretability in AI, though it is incremental in building on existing representation theories.
The paper investigates whether next-token prediction in large language models (LLMs) can learn human-interpretable concepts, establishing a theoretical identifiability result that shows LLM representations approximate posterior probabilities of latent discrete concepts up to a linear transformation, and validates this with evaluations on models like Pythia, Llama, and DeepSeek.
The remarkable achievements of large language models (LLMs) have led many to conclude that they exhibit a form of intelligence. This is as opposed to explanations of their capabilities based on their ability to perform relatively simple manipulations of vast volumes of data. To illuminate the distinction between these explanations, we introduce a novel generative model that generates tokens on the basis of human-interpretable concepts represented as latent discrete variables. Under mild conditions, even when the mapping from the latent space to the observed space is non-invertible, we establish an identifiability result, i.e., the representations learned by LLMs through next-token prediction can be approximately modeled as the logarithm of the posterior probabilities of these latent discrete concepts given input context, up to an invertible linear transformation. This theoretical finding not only provides evidence that LLMs capture underlying generative factors, but also provide a unified prospective for understanding of the linear representation hypothesis. Taking this a step further, our finding motivates a reliable evaluation of sparse autoencoders by treating the performance of supervised concept extractors as an upper bound. Pushing this idea even further, it inspires a structural variant that enforces dependence among latent concepts in addition to promoting sparsity. Empirically, we validate our theoretical results through evaluations on both simulation data and the Pythia, Llama, and DeepSeek model families, and demonstrate the effectiveness of our structured sparse autoencoder.