TomasD

Karma: 60

[Paper] A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

chanind, TomasD, hrdkbhatnagar and Joseph Bloom

25 Sep 2024 9:31 UTC

58 points

14 comments3 min readLW link

(arxiv.org)

TomasD’s Shortform

TomasD14 Mar 2024 15:03 UTC

1 point

0 comments1 min readLW link