Comment by gcr

wait, SVD / zeroing out the first principal component is an unsupervised technique. The earlier difference-of-means technique relies on the knowledge of which outputs are refusals and which aren’t. How would SVD be able to accomplish this without labels?

edit: the reference is https://arxiv.org/pdf/2512.18901

they are randomly sampling two sets of refusal/nonrefusal activation vectors, stacking them, and taking the elementwise difference between these two matrices. Then they use SVD to get the k top principal components. These are the directions they zero out.

Seems to me that the top principal component should be roughly equivalent to the difference-of-means vector, but wouldn’t the other PCs just capture the variance among the distributions of points sampled? I don’t understand why that’s desirable