@Connor Kissane @Neel Nanda Does SAE work on MLP blocks of GPT2-small as well? I find the recovery rate significantly low (40%) for MLP activations of larger models like GPT2-small.
@Connor Kissane @Neel Nanda Does SAE work on MLP blocks of GPT2-small as well? I find the recovery rate significantly low (40%) for MLP activations of larger models like GPT2-small.