INDEX

Explanations

numerical data points or references to specific measurements

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

Tokens appearing before a number

np_acts-logits-general · gemini-2.0-flash

easiest

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

RenderAtEndOf

-0.98

VersionUID

-0.73

HtmlAttribute

-0.72

DIPSETTING

-0.72

lapsingToolbar

-0.71

 تضيفلها

-0.66

utsal

-0.66

appé

-0.65

AndEndTag

-0.63

}}"

-0.58

POSITIVE LOGITS

 AssemblyProduct

0.59

 ostavi

0.55

 дописавши

0.47

migrationBuilder

0.46

 링크

0.45

Javadoc

0.45

Controllo

0.45

addCriterion

0.44

 Biôgrafia

0.43

сник

0.42

Activations Density 0.018%

numerical data points or references to specific measurements

Tokens appearing before a number

easiest

No Comments

No Known Activations

numerical data points or references to specific measurements

Tokens appearing before a number

easiest

No Comments

No Known Activations