JohnSteidley

Posts

Sorted by New

Comments

interpreting GPT: the logit lens

It doesn't sound hard at all. The things Gwern is describing are the same sort of thing that people do for interpretability where they, eg, find an image that maximizes the probability of the network predicting a target class.

Of course, you need access to the model, so only OpenAI could do it for GPT-3 right now.