Hugging Face's logo

serino28
/
probesae-checkpoints

English
sparse-autoencoder
mechanistic-interpretability
probing
gemma
llama
Model card Files
xet
 Community
probesae-checkpoints

Commit History

Update model card: de-anonymise, correct paper title and venue, document all three conditions and the per-family checkpoint layout
60ee48d
verified

serino28 commited on

add toxicity/llama/llama_L19_B1.0_N100000_E5.pt
757b230
verified

serino28 commited on

add toxicity/llama/llama_L19_B0.0_N100000.pt
1447aee
verified

serino28 commited on

add toxicity/llama/llama_L18_B1.0_N100000_E5.pt
ecd160b
verified

serino28 commited on

add toxicity/llama/llama_L18_B0.0_N100000.pt
b6d2c30
verified

serino28 commited on

add toxicity/llama/llama_L17_B1.0_N100000_E5.pt
8e9a821
verified

serino28 commited on

add toxicity/llama/llama_L17_B0.0_N100000.pt
db57f90
verified

serino28 commited on

add toxicity/llama/llama_L16_B1.0_N100000_E5.pt
052b64c
verified

serino28 commited on

add toxicity/llama/llama_L16_B0.0_N100000.pt
1b69c42
verified

serino28 commited on

add toxicity/gemma/gemma_L25_B1.0_N100000.pt
4b0cffb
verified

serino28 commited on

add toxicity/gemma/gemma_L25_B0.0_N100000_E5.pt
5c8d979
verified

serino28 commited on

add toxicity/gemma/gemma_L24_B1.0_N100000.pt
04ad068
verified

serino28 commited on

add toxicity/gemma/gemma_L24_B0.0_N100000_E5.pt
2ff141f
verified

serino28 commited on

add toxicity/gemma/gemma_L16_B1.0_N100000.pt
1f459fe
verified

serino28 commited on

add toxicity/gemma/gemma_L16_B0.0_N100000_E5.pt
9183adf
verified

serino28 commited on

add toxicity/gemma/gemma_L13_B1.0_N100000.pt
d4d59ec
verified

serino28 commited on

add toxicity/gemma/gemma_L13_B0.0_N100000_E5.pt
cf47d61
verified

serino28 commited on

add sentiment/llama/llama_L19_B1.0_N100000_E5.pt
e4380db
verified

serino28 commited on

add sentiment/llama/llama_L19_B0.0_N100000_E3.pt
88c3b4f
verified

serino28 commited on

add sentiment/llama/llama_L18_B1.0_N100000_E5.pt
4d481af
verified

serino28 commited on

add sentiment/llama/llama_L18_B0.0_N100000_E3.pt
3160fb8
verified

serino28 commited on

add sentiment/llama/llama_L17_B1.0_N100000_E5.pt
b36d8fa
verified

serino28 commited on

add sentiment/llama/llama_L17_B0.0_N100000_E3.pt
51b2d8a
verified

serino28 commited on

add sentiment/llama/llama_L16_B10.0_N100000_E5.pt
a0bc1da
verified

serino28 commited on

add sentiment/llama/llama_L16_B0.0_N100000_E3.pt
b9a68e2
verified

serino28 commited on

add sentiment/gemma/gemma_L25_B20.0_N100000_E5.pt
a818faa
verified

serino28 commited on

add sentiment/gemma/gemma_L25_B0.0_N100000_E5.pt
60a7e7f
verified

serino28 commited on

add sentiment/gemma/gemma_L24_B20.0_N100000_E5.pt
5a21e0f
verified

serino28 commited on

add sentiment/gemma/gemma_L24_B0.0_N100000_E5.pt
ad97c24
verified

serino28 commited on

add sentiment/gemma/gemma_L23_B10.0_N100000_E5.pt
49cb658
verified

serino28 commited on

add sentiment/gemma/gemma_L23_B0.0_N100000_E5.pt
f41d11d
verified

serino28 commited on

add sentiment/gemma/gemma_L22_B20.0_N100000_E5.pt
38f70e2
verified

serino28 commited on

add sentiment/gemma/gemma_L22_B0.0_N100000_E5.pt
1f88bbf
verified

serino28 commited on

add model card
ef6f2fc
verified

serino28 commited on

initial commit
67ed827
verified

serino28 commited on