INDEX

Explanations

code-related syntax elements and comments

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

\{\\

-0.60

makeText

-0.54

SharedCtor

-0.53

BeginInit

-0.53

 Económica

-0.52

 prophylaxis

-0.51

twimg

-0.50

])):

-0.49

AccessFile

-0.49

 chauss

-0.49

POSITIVE LOGITS

end

1.55

 ending

1.42

 ended

1.41

End

1.39

END

1.39

 ends

1.34

End

1.31

 finished

1.27

 finish

1.26

 finishes

1.23

Activations Density 1.002%

code-related syntax elements and comments

No Comments

No Known Activations