INDEX

Explanations

references to male and female gender distinctions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

GIP

-0.85

 Sitten

-0.84

 itſelf

-0.82

 Надо

-0.82

YAP

-0.80

 Notion

-0.79

 intonation

-0.76

 ConstraintSet

-0.76

 sabbia

-0.76

yntaxException

-0.75

POSITIVE LOGITS

 Male

0.93

MALE

0.89

 male

0.88

emale

0.85

 MALE

0.82

 males

0.79

FEMALE

0.79

 Females

0.76

Male

0.76

 female

0.76

Activations Density 0.065%

references to male and female gender distinctions

No Comments

No Known Activations

references to male and female gender distinctions

No Comments

No Known Activations