It’s essentially training an SAE on the concatenation of the residual stream from the base model and the chat model. So, for each prompt, you run it through the base model to get a residual stream vector v_b, through the chat model to get a residual stream vector v_c, and then concatenate these to get a vector twice as long, and train an SAE on this (with some minor additional details that I’m not getting into)
It’s essentially training an SAE on the concatenation of the residual stream from the base model and the chat model. So, for each prompt, you run it through the base model to get a residual stream vector v_b, through the chat model to get a residual stream vector v_c, and then concatenate these to get a vector twice as long, and train an SAE on this (with some minor additional details that I’m not getting into)
I got it, thank you very much!