INDEX

Explanations

references to gender differences in activities and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

łbym

-0.89

łem

-0.73

אתה

-0.70

Grandpa

-0.69

 brotherhood

-0.69

 Grandpa

-0.68

 grandpa

-0.66

łeś

-0.66

attore

-0.64

 seines

-0.63

POSITIVE LOGITS

 women

1.69

 Women

1.58

Women

1.51

women

1.48

 feminist

1.46

 female

1.40

 girls

1.39

 Girls

1.34

 womanhood

1.33

 woman

1.33

Activations Density 1.190%

references to gender differences in activities and preferences

No Comments

No Known Activations