Nick Cammarata's interpretability essay goes viral, sparks features-vs-mechanisms debate
inductionheads · x · 2026-10-17
Nick Cammarata says his informal research essay on neurons unexpectedly went viral, triggering unusually rich mechanistic interpretability discussions: whether to think in features or mechanisms, how much weak activations matter, and how scale changes things. He clarified the piece was an "informal essay and working hypothesis" with citations only for the basic story, the rest living in their still-unfinished technical paper; he has now added citations and thanked collaborator @curttigges for the language neuron research.
More from Research
- LeanGraphSearch mines Mathlib dependency graphs, lifting proof success to 81% — kaiwei_chang · 2026-10-17
- Kornia ships open-source Rust SLAM pipeline, seeking battle testers — kornia_foss · 2026-10-17
- Perplexity decider v1.2 lands #3 on Decision Index as longer training erodes backbone skills — antoine_chaffin · 2026-10-17
- Perplexity traces decider v1.2 regressions to longer training, mitigates via model souping — antoine_chaffin · 2026-10-17
- Packing multiple questions into one forward pass saves compute but adds instability — antoine_chaffin · 2026-10-17
- pplx-decider packs multiple questions per state into one bidirectional forward pass — antoine_chaffin · 2026-10-17