LESSWRONG
LW

2649
Good Man
0010
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No posts to display.
No wikitag contributions to display.
A Mechanistic Interpretability Analysis of Grokking
Good Man3y10

I found your idea fascinating.  You have a good company too. Percy Liang's group just published a paper along this line of thought and showed transformer's effectiveness in learning "ML trainers":

What Can Transformers Learn In-Context? A Case Study of Simple Function Classes

https://arxiv.org/abs/2208.01066

Reply