This thread reminds me that comparing feature absorption in SAEs with tied encoder / decoder weights and in end-to-end SAEs seems like valuable follow up.
Semi-relatedly, since most (all) of the SAE work since the original paper has gone into untied encoded/decoder weights, we don’t really know whether modern SAE architectures like Jump ReLU or TopK suffer as large of a performance hit as the original SAEs do, especially with the gains from adding token biases.
This thread reminds me that comparing feature absorption in SAEs with tied encoder / decoder weights and in end-to-end SAEs seems like valuable follow up.
Another approach would be to use per-token decoder bias as seen in some previous work: https://www.lesswrong.com/posts/P8qLZco6Zq8LaLHe9/tokenized-saes-infusing-per-token-biases But this would only solve it when the absorbing feature is a token. If it’s more abstract then this wouldn’t work as well.
Semi-relatedly, since most (all) of the SAE work since the original paper has gone into untied encoded/decoder weights, we don’t really know whether modern SAE architectures like Jump ReLU or TopK suffer as large of a performance hit as the original SAEs do, especially with the gains from adding token biases.