INDEX

Explanations

instances of formatting characters or placeholders, particularly in code-like contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 مشين

-0.88

tagHelperRunner

-0.84

QMetaType

-0.71

ReusableCell

-0.69

LEncoder

-0.68

 Centra

-0.66

 Jefus

-0.65

 Atti

-0.64

 Theodo

-0.64

saraba

-0.64

POSITIVE LOGITS

//

0.81

jooq

0.75

 désigne

0.64

Obrázky

0.59

 عمان

0.57

″]

0.57

maire

0.56

\}\\

0.56

 Woodbury

0.55

SMA

0.55

Activations Density 0.343%

instances of formatting characters or placeholders, particularly in code-like contexts

No Comments

No Known Activations