This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Connor Kissane
Posts
Sorted by New
Wikitag Contributions
Comments
Sorted by
Newest
41
White Box Control at UK AISI - Update on Sandbagging Investigations
2mo
5
34
SAEs are highly dataset dependent: a case study on the refusal direction
10mo
0
23
Open Source Replication of Anthropic’s Crosscoder paper for model-diffing
10mo
3
35
Base LLMs refuse too
1y
10
28
SAEs (usually) Transfer Between Base and Chat Models
1y
0
18
Attention Output SAEs Improve Circuit Analysis
1y
0
34
We Inspected Every Head In GPT-2 Small using SAEs So You Don’t Have To
2y
0
28
Attention SAEs Scale to GPT-2 Small
2y
0
35
Sparse Autoencoders Work on Attention Layer Outputs
2y
3
Comments