An Intro to Mechanistic Shaping Goodfire's "Mechanistic Shaping" technique steers a model's training objective using its internal representations, distinguishing "expression" (whether a concept is present in the representation) from "reliance" (how much that concept drives inference), according to a blog post summarizing the company's paper. The post's author recreated the effect on a smaller MNIST variant where a model classifying the left digit learned to rely on the identical right digit, then used averaged representation shifts across digit pairs to span a "concept subspace" and reshape that reliance. The approach offers an alternative to rebalancing datasets when correcting spurious correlations is impractical. An Intro to Mechanistic Shaping I recently read this great blog post by Goodfire on what they are calling Mechanistic Shaping