[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

[hexaga]

Indeed.

Taking the top principal component pattern matches as 'more surgical / targeted' so the LLM staples it on (consider prompts like: make this method stop degrading model performance). It ignores that _what_ is being targeted is as or more important than that 'something' is being targeted. But that's LLMs for you.

(in case it isn't immediately obvious, that paper is AI written too)