Building up toy transformer models by hand that work … that’s super interesting, both for interpretability and also education.
I put up the site [here](https://igor0.github.io/hand/distill/) for now. MadHatter, let me know if you want me to take it down.
Building up toy transformer models by hand that work … that’s super interesting, both for interpretability and also education.
I put up the site [here](https://igor0.github.io/hand/distill/) for now. MadHatter, let me know if you want me to take it down.