Neuroscientist maps brain mixed selectivity to polysemanticity in mech interp
HistedLab · x · 2026-10-18
In a mech interp discussion, HistedLab notes that mixed selectivity in neuroscience maps directly to polysemanticity in mechanistic interpretability. He adds that polysemanticity and messy representations in brains don't prove AI systems can't be trained to produce clean ones — though his feeling is it's inherent to highly nonlinear function-fitting.
Related event: Neuroscientist HistedLab on brain polysemanticity and AI interpretability(6 posts)→
More from AGI Musings
- Miles Brundage: No AI company is secure against state attackers — Miles_Brundage · 2026-10-18
- How user-built AI apps could replace the ad economy with a token economy — xiaosun86 · 2026-10-18
- Fields Medalist Timothy Gowers: one-shotting a proof with ChatGPT means we don't understand it — haider1 · 2026-10-18
- When users write their own apps, the ad economy gives way to token-based economics — xiaosun86 · 2026-10-18
- Peter Drucker's 1963 quote on efficiency resurfaces as a sharp critique of AI in 2026 — mattbeane · 2026-10-18
- Aligning AI: hard engineering problem or existential threat? A three-hypothesis breakdown — sayashk · 2026-10-18