EkdeepL: interpretability "neurons" are MLP hidden units, not neuroscience neurons
EkdeepL · x · 2026-10-17
In a discussion of @nickcammarata's interpretability results, researcher EkdeepL stresses a key subtlety: the "neurons" in this work are MLP hidden units feeding the residual stream, which differ from what neuroscience calls neurons. Monosemanticity is not being claimed for the latter, and no such results were found in this project or shown in literature. Context notes MLP-neuron monosemanticity already has substantial prior results.
More from AGI Musings
- The teamsters lesson: automation adjustment is least painful when newcomers just stop entering — soumitrashukla9 · 2026-10-23
- Researcher pushes back on AI cyber fear: 'labs selling defense by spreading fear' — gerardsans · 2026-10-23
- Nina Schick: compute shortage is itself a tremendous cybersecurity risk — NinaDSchick · 2026-10-23
- Investor: If AI is a bubble, it's the weirdest one ever seen — robleclerc · 2026-10-23
- Chamath: Banks will block AI agents via terms of service before anything else — nicolechirps · 2026-10-23
- AI researcher: Claude finally finished tedious research tasks I gave up on years ago — MikePFrank · 2026-10-23