On the Versatility of Sparse Autoencoders for In-Context Learning

摘要

Sparse autoencoders (SAEs) are emerging as a key analytical tool in the field of mechanistic interpretability for large language models (LLMs). While SAEs have primarily been used for interpretability, we shift focus and explore an understudied question: “Can SAEs be applied to practical tasks beyond interpretability?” Given that SAEs are trained on billions of tokens for sparse reconstruction, we believe they can serve as effective extractors, offering a wide range of useful knowledge that can benefit practical applications. Building on this motivation, we demonstrate that SAEs can be effectively applied to in-context learning (ICL). In particular, we highlight the utility of the SAE-reconstruction loss by showing that it provides a valuable signal in ICL—exhibiting a strong correlation with LLM performance and offering a powerful unsupervised approach for prompt selection. These findings underscore the versatility of SAEs and reveal their potential for real-world applications beyond interpretability. Our code is available at https://github.com/ihcho2/SAE-GPS.