行业动态
God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniques

God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniques
摘要: A modern AI has millions of neurons ... researchers started by seeking a 1:1 mapping between neurons and concepts, like a neuron that always fired whe
正文
A modern AI has millions of neurons ... researchers started by seeking a 1:1 mapping between neurons and concepts, like a neuron that always fired when the AI was thinking about cats, but quickly learned that nothing like that existed. Their first big breakthrough came in ...