INDEX

Explanations

references to gender, specifically male and female

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

-0.77

ap

-0.70

 ?>">

-0.70

 Conquer

-0.65

"]

-0.65

 }}"></

-0.64

ed

-0.64

YAP

-0.64

man

-0.64

dill

-0.63

POSITIVE LOGITS

 male

1.91

 Male

1.86

 MALE

1.80

 female

1.78

 FEMALE

1.75

 Female

1.71

Male

1.71

MALE

1.69

Female

1.65

female

1.62

Activations Density 0.087%

references to gender, specifically male and female

No Comments

No Known Activations