INDEX

Explanations

mentions of women or gender-related topics

oai_token-act-pair · gpt-3.5-turbo

references to women and gender issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•Gender Features

No Comments

Negative Logits

REDACTED

-0.86

opher

-0.76

asper

-0.76

anoia

-0.75

ebus

-0.75

rador

-0.75

eme

-0.74

ype

-0.72

RAY

-0.72

UFF

-0.71

POSITIVE LOGITS

folk

1.21

 empowerment

1.07

 genital

1.00

 reproductive

0.92

opausal

0.88

 breasts

0.87

 menstru

0.87

 genitals

0.86

 entrepreneurs

0.81

 nipples

0.80

Activations Density 0.086%

mentions of women or gender-related topics

references to women and gender issues

No Comments

No Known Activations