This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
AI ALIGNMENT FORUM
AF
Login
Dmitrii Kharlapenko
Posts
Sorted by New
8
Evolutionary prompt optimization for SAE feature visualization
10d
0
12
SAE features for refusal and sycophancy steering vectors
1mo
0
17
Extracting SAE task features for in-context learning
3mo
0
25
Self-explaining SAE features
4mo
0
Wiki Contributions
Comments
Sorted by
Newest