Hugging Face's logo
Activity Feed

AI & ML interests

Mechanistic interpretability

Recent Activity

goodfire-maxsloef  new activity about 1 month ago
Goodfire/DeepSeek-R1-SAE-l37:Expansion factor same on logic vs. math?
mbiss  published a model 5 months ago
Goodfire/Hackathon-gpt-oss-20b-SAE-l15
mbiss  updated a model 5 months ago
Goodfire/Hackathon-gpt-oss-20b-SAE-l15
View all activity

goodfire-maxsloef 
in Goodfire/DeepSeek-R1-SAE-l37 about 1 month ago

Expansion factor same on logic vs. math?

1
#2 opened about 1 month ago by
AISafety
mbiss 
published a model 5 months ago
mbiss 
updated a model 5 months ago
danieljbalsam 
updated a model 7 months ago
danieljbalsam 
published a model 7 months ago
mbiss 
published a model 8 months ago
mbiss 
updated a model 8 months ago
goodfire-maxsloef 
in Goodfire/DeepSeek-R1-SAE-l37 8 months ago

intuition behind layer selection

1
#1 opened 8 months ago by
ada-flo
goodfire-maxsloef 
updated a model 9 months ago
dron-h 
updated a dataset 9 months ago
dron-h 
updated a model 9 months ago
danieljbalsam 
published a dataset 9 months ago
danieljbalsam 
published a model 9 months ago
namgoodfire 
updated 6 models about 1 year ago