INDEX

Explanations

references to male and female gender distinctions 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 @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 Notion

-0.78

Things

-0.75

ed

-0.73

things

-0.71

man

-0.70

ap

-0.69

uğ

-0.68

 عج

-0.66

THINGS

-0.66

 Tutto

-0.65

POSITIVE LOGITS

 Male

1.39

 MALE

1.37

MALE

1.31

 male

1.27

 males

1.20

Male

1.18

 Males

1.16

 FEMALE

1.15

 Females

1.11

Males

1.08

Activations Density 0.074%

references to male and female gender distinctions in various contexts

No Comments

No Known Activations