INDEX

Explanations

references to software licenses and permissions

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

programming-related terms and links found in code snippets

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

commands and methods

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

stateProvider

-0.58

 الرياضيه

-0.56

ValueStyle

-0.56

 kří

-0.54

userdetails

-0.52

 pinulongan

-0.48

test

-0.47

 nhau

-0.47

تقاوى

-0.46

any

-0.46

POSITIVE LOGITS

HtmlAttribute

0.63

ApiOperation

0.62

SharedCtor

0.60

NUMX

0.57

})*/

0.54

Atsauces

0.54

 nahilalakip

0.54

 кӀ

0.53

ButtonText

0.52

bigsqcup

0.52

Activations Density 0.059%

references to software licenses and permissions

programming-related terms and links found in code snippets

commands and methods

No Comments

No Known Activations