INDEX

Explanations

coding syntax and structure

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

Followed by a file extension or URL

np_acts-logits-general · gemini-2.0-flash

// comments and slashes

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

">—

-0.56

">${

-0.55

شكرا

-0.54

RUE

-0.52

endwhile

-0.51

raszam

-0.51

">'.$

-0.48

ConverterFactory

-0.48

 endwhile

-0.48

以上

-0.48

POSITIVE LOGITS

tagHelperRunner

0.81

AddTagHelper

0.72

TagMode

0.70

findpost

0.60

 CreateTagHelper

0.60

 educator

0.54

 defaultstate

0.53

GEBURTS

0.53

 UITableViewCell

0.52

ⓧ

0.52

Activations Density 0.008%

coding syntax and structure

Followed by a file extension or URL

// comments and slashes

No Comments

No Known Activations