INDEX

Explanations

references to classification and CSS styles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Hauptartikel

-0.72

mayr

-0.65

tituted

-0.60

institution

-0.60

 élimin

-0.57

 Créez

-0.56

institutions

-0.56

 moindre

-0.55

endola

-0.55

oughby

-0.55

POSITIVE LOGITS

Age

0.97

Age

0.95

 ageing

0.90

 Aging

0.83

PerformLayout

0.78

css

0.76

 '\\;'

0.74

 aging

0.70

AGE

0.69

 Aged

0.69

Activations Density 0.100%

references to classification and CSS styles

No Comments

No Known Activations