I had a question the other day and figured I’ll post it here. Do we have any idea what would happen if we used the steering vector of the input itself?
For example : Take sentenceA, pass it through the LLM, store its embedding, take once again sentenceA, pass it through the LLM while adding the embedding.
As is, this would simply double the length of the hidden vector, but I’m wondering what would happen if we took played instead with the embedding say after the 5th token of sentenceA and add it at the 3rd token.
Similarly, would anything interesting happen with substraction? with adding a random orthogonal vector?
Hi,
I had a question the other day and figured I’ll post it here. Do we have any idea what would happen if we used the steering vector of the input itself?
For example : Take sentenceA, pass it through the LLM, store its embedding, take once again sentenceA, pass it through the LLM while adding the embedding.
As is, this would simply double the length of the hidden vector, but I’m wondering what would happen if we took played instead with the embedding say after the 5th token of sentenceA and add it at the 3rd token.
Similarly, would anything interesting happen with substraction? with adding a random orthogonal vector?
Thanks