alt Hacker NewsInteresting. Is there a paper that explains this in a bit more detail, like [0] for abliteration (underlying the Heretic software, afaik)?
Interesting. Is there a paper that explains this in a bit more detail, like [0] for abliteration (underlying the Heretic software, afaik)?
That paper you linked has all of the information you need. The linear algebra they do on the weights there to null out one direction reduces to a single (dot-product + broadcast-multiply + add) on the activations.