INDEX

Explanations

code-related tokens/keywords such as "begin", "end", and variable types

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 simplifié

-0.59

})));

-0.59

}))

-0.59

"):

-0.59

.")

-0.55

 ویکی‌پدیا

-0.55

ADELPHIA

-0.54

]:

-0.54

"]}

-0.52

 Económica

-0.51

POSITIVE LOGITS

end

1.49

End

1.39

end

1.34

END

1.33

End

1.26

END

1.23

 ends

1.02

ends

0.92

endif

0.90

 ended

0.87

Activations Density 1.151%

code-related tokens/keywords such as "begin", "end", and variable types

No Known Activations