LESSWRONG
LW

26
Srihita Vatsavaya
0010
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No posts to display.
No wikitag contributions to display.
Explaining the Transformer Circuits Framework by Example
Srihita Vatsavaya4mo10

2B) 

Hi there! Thanks for putting this together. Q - shouldnt this equation include a sum over heads term outside the m (MLP) function as well?

Reply