|
|
|
|
|
by hashmap
62 days ago
|
|
The native way to skip all that is train a small thingy to map hidden state -> token/thingy you care about once per model family, or just do it once and procrustes over the state from the model you're using to whatever you made the map for. |
|
I can't figure out if you meant that or not, it kinda fits. (No pun intended)