INDEX

Explanations

references to women

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

nyez

-0.64

 berea

-0.62

eldo

-0.62

elski

-0.62

ielli

-0.61

 Shetterly

-0.61

 Frankie

-0.60

ímite

-0.57

 esquerda

-0.56

ים

-0.56

POSITIVE LOGITS

 woman

2.25

 Woman

2.08

Woman

1.99

 WOMAN

1.90

woman

1.86

WOMAN

1.61

 mujer

1.15

 girl

1.01

 mulher

0.97

 Girl

0.95

Activations Density 0.077%

references to women

No Comments

No Known Activations