RSS

Daniel Lee

Karma: 27

In­ves­ti­gat­ing Sen­si­tive Direc­tions in GPT-2: An Im­proved Baseline and Com­par­a­tive Anal­y­sis of SAEs

Daniel Lee and StefanHex
6 Sep 2024 2:28 UTC
28 points
0 comments12 min readLW link