INDEX

Explanations

mentions of women in various contexts, suggesting a focus on gender-related content

oai_token-act-pair · gpt-3.5-turbo

references to women and women's issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

Not in Any Lists

No Comments

Negative Logits

rador

-0.79

UFF

-0.78

asper

-0.76

REC

-0.75

REDACTED

-0.75

ype

-0.74

opher

-0.73

ellect

-0.71

OWN

-0.70

-+-+

-0.70

POSITIVE LOGITS

folk

1.14

 empowerment

1.03

borg

0.90

 breasts

0.88

 contraceptive

0.87

 genital

0.86

hood

0.84

 menstru

0.84

opausal

0.83

 genitals

0.83

Activations Density 0.058%

mentions of women in various contexts, suggesting a focus on gender-related content

references to women and women's issues

No Comments

No Known Activations