0

Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models

Progress in interpretable dictionary learning for language models is evaluated using supervised metrics derived from chess and Othello transcripts, and enhanced by a new training technique called p-annealing.

Year
2024
Venue
arXiv 2024
Authors
9
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2408.00113v2ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

Abstract

What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the quality of these SAEs is difficult because we lack a ground-truth collection of interpretable features that we expect good SAEs to recover. We thus propose to measure progress in interpretable dictionary learning by working in the setting of LMs trained on chess and Othello transcripts. These settings carry natural collections of interpretable features -- for example, "there is a knight on F3" -- which we leverage into $\textit{supervised}$ metrics for SAE quality. To guide progress in interpretable dictionary learning, we introduce a new SAE training technique, $\textit{p-annealing}$, which improves performance on prior unsupervised metrics as well as our new metrics.

Authors

9