LESSWRONG
LW

4221
Igor Ostrovsky
4020
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No posts to display.
No wikitag contributions to display.
Teaser: Hard-coding Transformer Models
Igor Ostrovsky4y40

I (not the OP) put it up here for now: https://igor0.github.io/hand/distill/

I'll take it down if MadHatter asks me or once there is an official site.

Reply
Teaser: Hard-coding Transformer Models
Igor Ostrovsky4y20

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.

Reply