INDEX

Explanations

references to Europe and European identity

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

الإنجليزية

-0.53

toEqual

-0.49

 record

-0.49

Nexus

-0.49

 essential

-0.48

cap

-0.48

lit

-0.47

getBean

-0.47

<h2>

-0.47

 sign

-0.47

POSITIVE LOGITS

 EUROPEAN

0.82

Scénario

0.81

 Roskov

0.80

European

0.78

ReusableCell

0.76

 European

0.76

EUROPEAN

0.76

 europé

0.74

 européennes

0.73

 european

0.70

Activations Density 0.113%

references to Europe and European identity

No Comments

No Known Activations