INDEX

Explanations

words related to classification in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

ंदीखरीदारी

-0.83

roveň

-0.77

itao

-0.75

-0.74

 Lorde

-0.74

 Kitt

-0.74

expandindo

-0.72

 AssemblyCulture

-0.72

 Bhutan

-0.70

shadowOffset

-0.69

POSITIVE LOGITS

lassification

0.94

 classific

0.92

 Wyman

0.85

 Classi

0.84

}))

0.84

 classi

0.83

 McCulloch

0.82

Sve

0.82

']?>

0.82

Classi

0.79

Activations Density 0.165%

words related to classification in various contexts

No Comments

No Known Activations