INDEX

Explanations

references to "men" in various contexts and scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 HasFactory

-0.78

 мәкал

-0.75

localctx

-0.75

fjspx

-0.73

^(@)

-0.71

onActivityResult

-0.71

—

-0.71

VIAF

-0.69

})));

-0.66

$")

-0.66

POSITIVE LOGITS

Men

1.15

Men

1.06

MEN

1.02

men

1.00

MEN

0.89

men

0.80

 Women

0.69

 WOMEN

0.66

Women

0.65

 mene

0.63

Activations Density 0.070%

references to "men" in various contexts and scenarios

No Comments

No Known Activations