Sparse Autoencoders Reveal Interpretable Structure in Small Gene Language Models

Haoxiang Guan, Jiyan He, Jie Zhang

Keywords: AI, gene language models, sparse autoencoders

TL;DR: This paper shows that sparse autoencoders can extract biologically meaningful features from small gene language models, revealing both nucleotide patterns and transcription factor binding sites.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 270