INDEX

Explanations

references to judicial or legal entities, specifically "district" and "court."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 espagnole

-0.77

 अव

-0.76

 aliqu

-0.75

Lov

-0.75

sendMail

-0.74

ghum

-0.73

NESSEE

-0.72

 fumes

-0.71

 Programmer

-0.69

carolina

-0.69

POSITIVE LOGITS

 district

1.91

 District

1.88

 districts

1.80

 DISTRICT

1.79

District

1.75

DISTRICT

1.66

 Districts

1.62

district

1.60

districts

1.48

ricts

1.27

Activations Density 0.074%

references to judicial or legal entities, specifically "district" and "court."

No Comments

No Known Activations