INDEX

Explanations

numerical values and percentage expressions

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

Prime factorizations

np_acts-logits-general · gemini-2.0-flash

quantification and ranges

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 AssemblyCulture

-0.73

oa̍t

-0.66

وفاته

-0.54

 betweenstory

-0.52

 tarihinde

-0.52

aarrggbb

-0.51

亩

-0.48

 ProtoMessage

-0.48

Morfologia

-0.47

 famí

-0.47

POSITIVE LOGITS

VersionUID

0.59

Hochspringen

0.57

.*")]

0.56

 EdgeInsets

0.56

*/].

0.55

tagHelperRunner

0.54

CSRF

0.54

 мәкал

0.53

Bronnen

0.53

nestjs

0.53

Activations Density 0.582%

numerical values and percentage expressions

Prime factorizations

quantification and ranges

No Comments

No Known Activations