This is a special post for quick takes by leogao. Only they can create top-level comments. Comments here also appear on the Quick Takes page and All Posts page.
a take I've expressed a bunch irl but haven't written up yet: feature sparsity might be fundamentally the wrong thing for disentangling superposition; circuit sparsity might be more correct to optimize for. in particular, circuit sparsity doesn't have problems with feature splitting/absorption
