This seems true to me, though finding the right scaling curve for models is typically quite hard so the conversion to effective compute is difficult. I typically use CE loss change, not loss recovered. I think we just don’t know how to evaluate SAE quality.
My personal guess is that SAEs can be a useful interpretability tool despite making a big difference in effective compute, and we should think more in terms of useful they are for downstream tasks. But I agree this is a real phenomena, that is easy to overlook, and is bad.
This seems true to me, though finding the right scaling curve for models is typically quite hard so the conversion to effective compute is difficult. I typically use CE loss change, not loss recovered. I think we just don’t know how to evaluate SAE quality.
My personal guess is that SAEs can be a useful interpretability tool despite making a big difference in effective compute, and we should think more in terms of useful they are for downstream tasks. But I agree this is a real phenomena, that is easy to overlook, and is bad.