INDEX

Explanations

references to the USA

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 ?>">

-0.96

 Paral

-0.83

ly

-0.83

nders

-0.80

Bav

-0.78

Embedded

-0.76

 Ruman

-0.75

 Refle

-0.74

}>

-0.73

Ait

-0.73

POSITIVE LOGITS

 góry

0.75

DateField

0.72

 Fife

0.71

 Woodford

0.71

 Biscuit

0.70

wezen

0.70

 OPERATOR

0.69

 Dodson

0.69

OPERATOR

0.69

 Stans

0.68

Activations Density 0.480%

references to the USA

No Comments

No Known Activations