Goodfire research says neural networks are already clean
Neural Networks Are Already Clean - Goodfire
AI summary
Goodfire Research proposes that the cause of polysemy in early model organisms is not superposition, but several ordinary and mostly fixable problems. The organization says it can now understand most neurons in models with up to trillions of parameters, and believes the prospects for mechanistic interpretability may be far more optimistic than previously expected.
Why it was selected
Goodfire believes the cause of polysemy is not superposition but several fixable ordinary problems, and the prospects for mechanistic interpretability may be better than previously expected.
Read original