INDEX

Explanations

references to data and statistical information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

Nuorodos

-0.65

rawDesc

-0.56

gql

-0.55

 muualla

-0.53

ruptedException

-0.52

 dilutions

-0.51

ynku

-0.50

 dilution

-0.49

unggu

-0.49

ItemBackground

-0.48

POSITIVE LOGITS

 onOptions

0.79

 disambiguazione

0.76

 AssemblyCulture

0.73

webElementGuid

0.73

 JpaRepository

0.70

 Desk

0.68

urers

0.67

ATA

0.67

ыгана

0.66

 surla

0.66

Activations Density 0.054%

references to data and statistical information

No Comments

No Known Activations