A researcher says modern neural networks are far more interpretable than believed, with most neurons understandable in models up to trillions of parameters (Nick Cammarata/Goodfire)

Overview

Nick Cammarata / Goodfire: A researcher says modern neural networks are far more interpretable than believed, with most neurons understandable in models up to trillions of parameters — The cause of polysemanticity in early model organisms wasn't superposition, but several ordinary, mostly fixable issues.

SpinGraph analysis pending — check back after processing.