INDEX

Explanations

instances of the word "do" and its variations, indicating actions or capabilities

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

occurrences of the word "do."

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

following 'do'

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.20.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

*>(

-0.55

rawDesc

-0.48

 fört

-0.45

']?>

-0.45

maki

-0.45

 hine

-0.44

 sebagainya

-0.43

 habido

-0.43

ிக

-0.43

So

-0.43

POSITIVE LOGITS

 AssemblyCulture

0.96

intios

0.72

ंदीखरीदारी

0.63

LookAnd

0.62

 виправивши

0.61

+#+#

0.59

exitRule

0.58

UnknownFieldSet

0.57

 BoxDecoration

0.56

Carriera

0.56

Activations Density 0.038%

instances of the word "do" and its variations, indicating actions or capabilities

occurrences of the word "do."

following 'do'

No Comments

No Known Activations