INDEX

Explanations

indents or whitespace characters in the code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

get

-0.60

got

-0.51

war

-0.50

end

-0.48

 Voiture

-0.48

 vostri

-0.46

posten

-0.46

win

-0.46

 opened

-0.46

 give

-0.46

POSITIVE LOGITS

public

0.83

/**

0.81

ⓧ

0.74

expandindo

0.72

elemField

0.71

Autoritní

0.71

///

0.67

publ

0.67

private

0.57

+/**

0.56

Activations Density 0.015%

indents or whitespace characters in the code

No Comments

No Known Activations

indents or whitespace characters in the code

No Comments

No Known Activations