This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Fazl
Posts
Sorted by New
11
Early Experiments in Reward Model Interpretation Using Sparse Autoencoders
7mo
0
8
Automated Sandwiching & Quantifying Human-LLM Cooperation: ScaleOversight hackathon results
1y
0
Wiki Contributions
Comments