15 1 2

Arthur Conmy (GDM Account)

ArthurConmyGDM

https://arthurconmy.github.io/about

AI & ML interests

Interpretability, AI Safety, AI Alignment

Recent Activity

liked a model 20 days ago

google/gemma-scope

liked a model 23 days ago

fnlp/Llama-Scope

New activity 30 days ago

google/gemma-scope:suggestion: notate the canonical SAEs

View all activity

Organizations

ArthurConmyGDM's activity

New activity in google/gemma-scope 30 days ago

suggestion: notate the canonical SAEs

#9 opened about 1 month ago by

dribnet

New activity in google/gemma-scope-9b-pt-res 3 months ago

add experimental embedding SAEs

#4 opened 3 months ago by

Aric

New activity in google/gemma-scope-2b-pt-res 3 months ago

add experimental embedding SAEs

#7 opened 3 months ago by

Aric

New activity in google/gemma-scope 3 months ago

New table

#8 opened 3 months ago by

ArthurConmyGDM

New activity in google/gemma-scope-2b-pt-res 3 months ago

Link model to paper

#5 opened 3 months ago by

nielsr

New activity in google/gemma-scope 3 months ago

Link dataset to paper

#7 opened 3 months ago by

nielsr

Link model to paper

#6 opened 3 months ago by

nielsr

New activity in google/gemma-scope-9b-pt-res 4 months ago

The L0 of the SAE does not quite match

#3 opened 4 months ago by

ShayanShamsi

New activity in google/gemma-scope 4 months ago

Update README.md

#5 opened 4 months ago by

NeelNanda2

Update README.md

#4 opened 4 months ago by

NeelNanda2

Uploaded demo GIF

#3 opened 4 months ago by

NeelNanda2

New activity in google/gemma-scope-2b-pt-res 4 months ago

Update README.md

#4 opened 4 months ago by

ArthurConmy

New activity in google/gemma-scope-9b-pt-res 4 months ago

Update README.md

#2 opened 4 months ago by

ArthurConmy

New activity in google/gemma-scope-2b-pt-res 4 months ago

Update README.md

#3 opened 4 months ago by

ArthurConmyGDM

Delete layer_11/width_16k/average_l0_79

#2 opened 4 months ago by

ArthurConmyGDM

Delete layer_11/width_16k/average_l0_79

#2 opened 4 months ago by

ArthurConmyGDM