@neverrixxThere has been much discussion recently about how interpretable neurons in LLMs are. Today we're announcing our paper from January's cohort of Anthropic Fellows, where we show neurons may be a stronger basis for interpretability than commonly assumed. 🧵 (1/6)
@aryaman2020neurons 😎
@tszzlneural nets are already clean@neverrixxThere has been much discussion recently about how interpretable neurons in LLMs are. Today we're announcing our paper from January's cohort of Anthropic Fellows, where we show neurons may be a stronger basis for interpretability than commonly assumed. 🧵 (1/6)@aryaman2020neurons 😎@tszzlneural nets are already clean@neverrixxThere has been much discussion recently about how interpretable neurons in LLMs are. Today we're announcing our paper from January's cohort of Anthropic Fellows, where we show neurons may be a stronger basis for interpretability than commonly assumed. 🧵 (1/6)@aryaman2020neurons 😎@tszzlneural nets are already clean@neverrixxThere has been much discussion recently about how interpretable neurons in LLMs are. Today we're announcing our paper from January's cohort of Anthropic Fellows, where we show neurons may be a stronger basis for interpretability than commonly assumed. 🧵 (1/6)@aryaman2020neurons 😎@tszzlneural nets are already clean—
Not ranked yet
—
Not ranked yet
Comments