Models encode cities, people, proteins — too few neurons for one-per-entity monosemanticity
livgorton · x · 2026-10-18
Liv Gorton argues models must represent a vast range of content — cities, streets, businesses, real and fictional people, books, coding methods, proteins, species, molecules — and many neurons aren't for entity recognition at all. So neuron count likely can't cover entities one-by-one. The neurons may still be useful, but credible people are asserting the much stronger monosemanticity claim.
Related event: Monosemanticity debate: Does neuron count cap what a model can know?(8 posts)→
More from Research
- RFD4-Proteina's 'underrated' docs detail partial diffusion for protein redesign — AllThingsApx · 2026-10-23
- MPI-Sec PhD Thesis on Vulnerability Detection Benchmarks Includes Pre-LLM Classic "Top Score on the Wrong Exam" — mboehme_ · 2026-10-23
- LiveNerf's 29-day data finds no nerfing of Claude Opus 5.5 — TheOnlyVibemaster · 2026-10-23
- New paper makes 9 falsifiable predictions toward a major AI-enabled terror attack by 2027-2028 — StephenLCasper · 2026-10-23
- HumanoidPose recovers humanoid robots' full-body joint states from RGB video alone — cholz · 2026-10-23
- Sophont's Holon-S1 predicts genes and biomarkers from routine pathology slides — iScienceLuvr · 2026-10-23