If there are some very common features in particular layers (e.g. an ‘attend to BOS’ feature), then restricting one expert to be active at a time will potentially force SAEs to learn common features in every expert.
+1 to similar concerns—I would have probably left one expert always on. This should both remove some redundant features.
Hi Lee and Arthur, thanks for the feedback! I agree that routing to a single expert will force redundant features and will experiment with Arthur’s suggestion. I haven’t taken a close look at the router/expert geometry yet but plan to do so soon.
+1 to similar concerns—I would have probably left one expert always on. This should both remove some redundant features.
Hi Lee and Arthur, thanks for the feedback! I agree that routing to a single expert will force redundant features and will experiment with Arthur’s suggestion. I haven’t taken a close look at the router/expert geometry yet but plan to do so soon.