SILO: Revealing the Low Rank Structure of Language Models through Sequences of Logits

A major problem in the study of large language models, and deep learning more broadly, is to understand their inherent low-dimensional structure.  We introduce an approach to study the low-dimensional structure of language models at a model-agnostic level: as sequential probabilistic models. We first empirically demonstrate that a wide range of modern language models exhibit low-rank structure: in particular, matrices built from the model’s logits for varying sets of prompts and responses have low approximate rank. We then show that this low-rank structure can be leveraged for generation — in particular, we can generate a response to a target prompt using a linear combination of the model’s outputs on unrelated, or even nonsensical prompts.

On the theoretical front, we observe that studying the approximate rank of language models in the sense discussed above yields a simple universal abstraction whose theoretical predictions parallel our experiments. We then analyze the representation power of the abstraction and give provable learning guarantees.