Explaining Latents in Turing-LLM-1.0-254M with Pre-Defined Function Types

This paper focuses on labeling, i.e., writing explanations for features or latents. This is an interesting topic with some low-hanging fruit. There have been concerns about using other models to label features, as this could open the door for subversion by the labeling model. Another hackathon introduced a graph-based explanation approach. I think they haven’t properly explained how they derive results for their functions. They describe functions for specific tokens, connections between tokens, and topics. I’m not quite sure if this approach can scale or if it brings us much closer to converting features into code, but I still find this general direction interesting. Verifying that features function like code would be a significant step towards explanation label integrity.

This project attempts to overcome the issue of using LLMs to aid in scaling interpretability. More details on what each function does would make understanding the work easier. It'd be interesting to see if the additional functions in the appendix improve the performance on later layers. It'd also be nice to see if these ideas generalise to other LLMs (could be done with open sourced models with SAEs on all layers like Gemma 2B).

This project aims to find alternative ways of interpreting language model features rather than asking another LLM to interpret them. The method proposed is to use the structure of the synthetic data used to train TuringLLM to generate candidate feature labels, either from uni- and bigrams or from topic data extracted from the filenames.

These interpretation functions allow the authors to label the majority of features in the earlier layers of the model, but accuracy drops substantially past layer 4 of 12. I would be interested to see examples of unlabeled features in later layers to understand whether they are more abstract features, mostly related to output tokens, or mostly uninterpretable.

The presentation of the work could be improved by describing the evaluation process and the motivation behind the choice of functions in more detail. I'm also not sure how this is intended to generalise to more complex features in more powerful models - some insight into this would be valuable.

This project aims to develop programmatic methods for interpreting the internals of the Turing LLM. These methods rely on the statistics of the synthetic dataset used to train the base model. The writeup is a bit unclear as to what exactly these methods do, but the examples and function names give a decent picture. Figure 1 is interesting: it appears that topic and uni/bi-gram statistics dominate in the earlier layers, but later layers are relatively poorly explained - what is going on here? Potentially the last couple of layers could be explained by the _next_ token, which would be interesting to see.