This website requires javascript to properly function. Consider activating javascript to get access to all site functionality.
LESSWRONG
LW
Login
Alex Gibson
Posts
Sorted by New
1
Alex Gibson's Shortform
2mo
0
1
Using the probabilistic method to bound the performance of toy transformers
1mo
0
6
Contextual attention heads in the first layer of GPT-2
Ω
1mo
Ω
0
2
Duplicate token neurons in the first layer of GPT-2
2mo
0
1
Alex Gibson's Shortform
2mo
0
Wikitag Contributions
Comments
Sorted by
Newest