Training and interpreting a transformer to sort lists of variable length. From Neel Nanda's 200 concrete open problems in mechanistic interpretability. in progress.
Trained a 1 layer 4 head attn only transformer
Accuracies
-
Notifications
You must be signed in to change notification settings - Fork 0
Jordine/interp_variable_list
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
training a transformer to sort variable length list, and doing interp on it. in progress.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published