Negative Results for Sparse Autoencoders On Downstream Tasks and Deprioritising SAE Research…

Negative Results for Sparse Autoencoders On Downstream Tasks and Deprioritising SAE Research (Mechanistic Interpretability Team Progress Update) Lewis Smith*, Sen Rajamanoharan*, Arthur Conmy, Callum McDougall, Janos Kramar, Tom Lieberum, Rohin Shah, Neel Nanda * = equal contribution The following piece is a list of snippets about research from the GDM mechanistic interpretability team, which we didn’t consider a good fit for turning into a paper, but which we thought the community might benefit from seeing in this less formal form.