Comment Author | Post | Deleted By User | Deleted Date | Deleted Public | Reason |
---|---|---|---|---|---|
Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small | leogao | 2mo | false | ||
Discussion: Challenges with Unsupervised LLM Knowledge Discovery | Clément Dumas | 3mo | true | Sorry I didn't understand you were confused because of the visualization | |
Evaluating the historical value misspecification argument | Daniel Kokotajlo | 4mo | true | Accidental duplicate | |
Evaluating the historical value misspecification argument | Daniel Kokotajlo | 4mo | true | Accidental duplicate | |
TurnTrout's shortform feed | Ben Pace | 4mo | false | ||
TurnTrout's shortform feed | Ben Pace | 4mo | false | ||
Coup probes: Catching catastrophes with probes trained off-policy | Fabien Roger | 4mo | false | ||
Preventing Language Models from hiding their reasoning | Fabien Roger | 5mo | true | ||
Thoughts on responsible scaling policies and regulation | Lukas Finnveden | 5mo | false | ||
RSPs are pauses done right | Davidmanheim | 5mo | false | I reflected on this and realized I was being unfair. |
Author | Post | Banned Users |
---|---|---|
Asymptotically Unambitious AGI |
ID | Banned From Frontpage | Banned from Personal Posts |
---|---|---|
[anonymous] | ||
User | Ended at | Type |
---|---|---|
13d | allComments | |
21d | allComments | |
7d | allComments | |
16d | allComments | |
6d | allComments | |
2mo | allPosts | |
2mo | allComments |