INDEX

Explanations

references to men and gender roles

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

expandindo

-0.96

 snippetHide

-0.85

 EconPapers

-0.82

 nakalista

-0.82

 محفوظة

-0.81

Viited

-0.79

 onCreateView

-0.75

titleMargin

-0.74

']")

-0.74

CloseOperation

-0.72

POSITIVE LOGITS

men

0.81

Men

0.78

MEN

0.69

who

0.68

Man

0.63

Men

0.62

man

0.60

hunt

0.59

men

0.56

 woman

0.55

Activations Density 0.084%

references to men and gender roles

No Comments

No Known Activations