LessWrong15 min read
Sanity Checks for Sanity Checks for Sparse Autoencoders
This post will probably not be very informative to readers who don't know what an SAE (Sparse Autoencoder) is.An interpretability researcher once told me, "SAEs can never fail, they can only be failed." But recently, SAEs have been suffering failure after failure, and as a result, the field has…
By Celene NightingaleLessWrong

Read the full story
Originally published by LessWrong on Oct 31, 2026.
Comments
Sign in to join the discussion.