Nice, that makes sense. I agree that RepE / LAT might not be helpful as terminology. “Unsupervised probing” is more straightforward and descriptive.
(Note that in this work, we’re just doing supervised probing though we do use models to generate some of the training data.)
Nice, that makes sense. I agree that RepE / LAT might not be helpful as terminology. “Unsupervised probing” is more straightforward and descriptive.
(Note that in this work, we’re just doing supervised probing though we do use models to generate some of the training data.)