representations
Everything on Ground Truth tagged “representations” — 2 items.
Principal component analysis: finding the directions that summarize your data Lesson
Principal component analysis compresses a dataset into perpendicular directions that preserve the most variation, without guaranteeing useful or causal features.
Activation steering: changing a model's behaviour by editing its thoughts Lesson
Activation steering changes what an AI model does by adding or subtracting a direction from its internal numbers while it runs, with no retraining and no prompt changes, and the fact that it works at all says something uncomfortable about how safety training is stored.