#Polysemanticity in early models arose from fixable #architecturalissues, not superposition. #Recursivegeneralisation explains most cases, making networks broadly legible. Improved tools show #highinterpretability in #models up to trillions of parameters, supporting direct study. https://already-clean.goodfire.com/?AIagents.at #AIagent #AI #ML #NLP #LLM #GenAI
#polysemanticity — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #polysemanticity, aggregated by home.social.