原书出处
Designing Large Language Model Applications
single neuron can be activated for many different types of input. Thus, any given neuron’s exact contribution is not entirely clear. The researchers introduced the notion of features, linear combinations of multiple neuron activations. They show that these features are more interpretable than a single neuron, as each feature is activated only on a single type of input. Some features are activated only on a
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Designing Large Language Model Applications/_epub-src/OEBPS/ch05.html
EPUB SHA-256:1b4d2347fec2f949fcddfbaf4fad597a1ae20887a096cfae64c59a619b4781bf