Makes sense! Thanks! In that case, we can potentially reduce the width, which might (along with a smaller dataset) help scale saes to understanding mechanisms in big models?
Great work! Is there something like too narrow of a dataset? For refusal, what do you think happens if we specifically train on a bunch of examples that show signs refusal?
Makes sense! Thanks! In that case, we can potentially reduce the width, which might (along with a smaller dataset) help scale saes to understanding mechanisms in big models?