INDEX

Explanations

code-related keywords or syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

adaptiveStyles

-0.65

 TestBed

-0.60



-0.58

 jLabel

-0.57

 commiss

-0.57

OGND

-0.57

GEBURTS

-0.56

esModule

-0.55

 tume

-0.54

ſelf

-0.53

POSITIVE LOGITS

Kjelder

0.54

ppelin

0.54

 ostavi

0.54

帖最后由

0.52

 davon

0.51

 eslint

0.48

NewGuid

0.48

还

0.46

stateProvider

0.46

omla

0.46

Activations Density 0.062%

code-related keywords or syntax

No Comments

No Known Activations