Fazl

Karma: 18

Early Experiments in Reward Model Interpretation Using Sparse Autoencoders

lukemarks, Amirali Abdullah, Rauno Arike, Fazl and nothoughtsheadempty

3 Oct 2023 7:45 UTC

11 points

0 comments5 min readLW link

Automated Sandwiching & Quantifying Human-LLM Cooperation: ScaleOversight hackathon results

Esben Kran, Fazl, Sabrina Zaki, gabrielrecc and rz2383

23 Feb 2023 10:48 UTC

8 points

0 comments6 min readLW link