Mech Interp is a Verifiable Task

If we think parts of MLP0-MLP3 are computing [a sorting algorithm], we can replace those parts with [a sorting algorithm] and check reconstruction loss.[1] However, reconstruction loss is not enough.Suppose we replace MLP0 with two things:Its mean activation - simple, but poor reconstructionMLP0 - perfect reconstruction, but no reduction in complexityWe can visualize this as a pareto frontier trading off reconstruction with "simplicity". Ideally we achieve perfect reconstruction with perfect sim...