INDEX

Explanations

references to gender and gender-based distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 }}"></

-0.83

 Davie

-0.82

 "'");

-0.78

سطس

-0.76

]();

-0.74

 Sigurd

-0.74

Πηγή

-0.74

 estekak

-0.73

('.');

-0.72

tonsoft

-0.72

POSITIVE LOGITS

 gender

1.63

 Gender

1.46

gender

1.40

Gender

1.30

 genders

1.11

GENDER

1.10

sex

0.92

 sexo

0.84

Sex

0.82

 transgender

0.82

Activations Density 0.109%

references to gender and gender-based distinctions

No Comments

No Known Activations