SAEScientist-Bench

Mentions · 7d0
Mentions · 30d0
All mentions1
First seenSep 8, 2026
Last mentionedSep 8, 2026

Timeline

1 articles · newest first

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

SAEScientist-Bench tests whether AI agents can autonomously run SAE interpretability research on Gemma-2-9B-IT; frontier agents trail expert baselines.

arXiv cs.AI / cs.LG / cs.CLSep 8, 17:45 UTC · Sep 8, 2026AI research3 · 1 read

Appears with

Gemma Scopeproduct · 1
Gemma-2-9B-ITai model · 1
Neuronpediaproduct · 1

Entities are extracted by the model from each article. First seen Sep 8, 2026, last mentioned Sep 8, 2026. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.