QA2 min read
From Error Prediction to Causal Influence: Auditing SAE Features in Multiple-Choice QA
Sparse autoencoders (SAEs) can predict internal features associated with model errors, but association alone does not establish causal influence. We study this distinction in multiple-choice question answering, where answer preference can be measured by the logit margin between the correct answer…
By Aria Nourbakhsh, Adelaide Danilov, Oleksandr Marchenko Breneur, Salima LamsiyaharXiv - cs.CL (NLP)
Read the full story
Originally published by arXiv - cs.CL (NLP) on Oct 30, 2026.
Comments
Sign in to join the discussion.