Bing Chat neuron found in public neuron dataset, Claude reveals the lookup path
Sauers_ · x · 2026-10-31
Follow-up to the persona neuron thread: Sauers asked Claude how such neurons were found and was told to check @jfonsecarivera's neuron dataset, where the result — including a neuron labeled "BING CHAT NEURON" — was already cataloged.
The takeaway: open neuron datasets are becoming reusable infrastructure for interpretability research, letting researchers retrieve known feature neurons instead of analyzing from scratch.
Related event: Researchers identify "Bing Chat neuron" that steers model persona(2 posts)→
More from Research
- Prune-then-loop retrofit turns a pretrained VLM recurrent, beating baseline with 23.3% fewer language params — HildeKuehne · 2026-10-31
- Microsoft Research open-sources Agensh: 1,024 coding agents, no boss, 55% on Pandoc rebuild — JafarNajafov · 2026-10-31
- Tsinghua team's ActionCodec2 streams action tokens per step, hitting 46.2% grasp vs FAST's 9.2% — ZeYanjie · 2026-10-31
- OpenAI leak's hidden gem: a Log-Sobolev result completing KLS picture — IgorCarron · 2026-10-31
- "Probably present": A Visual Explainer of How Bloom Filters Work — YashasGunderia · 2026-10-31
- S2COPE discovers interpretable visual concepts from unlabeled images — burkov · 2026-10-31