I've made some interesting strides in AI interpretability: recasting trained neural nets into a geometry where you can read them exactly, with arithmetic — the exact counterpart of Anthropic's averaged "J-lens," including (I believe) the first measurement of how lossy averaged lenses actually are.
It's a deep collaboration between me (the human author) and Claude, so rather than crosspost the text itself — which would run against LessWrong's AI-writing policy — I'm linking it. I'd love it if you took a look and left your comments here.
I've made some interesting strides in AI interpretability: recasting trained neural nets into a geometry where you can read them exactly, with arithmetic — the exact counterpart of Anthropic's averaged "J-lens," including (I believe) the first measurement of how lossy averaged lenses actually are.
The full series — eight posts, with embedded interactive widgets — is here: https://doinfinitely.github.io/legible-networks/
It's a deep collaboration between me (the human author) and Claude, so rather than crosspost the text itself — which would run against LessWrong's AI-writing policy — I'm linking it. I'd love it if you took a look and left your comments here.