This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Daniel Lee
Posts
Sorted by New
53
Finding Features Causally Upstream of Refusal
3mo
5
28
Investigating Sensitive Directions in GPT-2: An Improved Baseline and Comparative Analysis of SAEs
8mo
0
Wikitag Contributions
Comments
Sorted by
Newest
Open Thread Summer 2024
Daniel Lee
8mo
8
0
Hi, excited to learn more about Mech Int!
Reply
Hi, excited to learn more about Mech Int!