INDEX

Explanations

mentions of gender, specifically focusing on males

oai_token-act-pair · gpt-3.5-turbo

mentions of the word "male."

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

 GOODMAN

-0.80

krit

-0.77

heet

-0.75

etsk

-0.73

leans

-0.72

arella

-0.69

rep

-0.69

duration

-0.68

xtap

-0.66

today

-0.66

POSITIVE LOGITS

volent

1.84

 genital

1.01

vol

0.97

 ejac

0.93

 genitals

0.88

 infertility

0.85

 supremacy

0.81

 circumcision

0.79

 supremacist

0.79

 reproductive

0.78

Activations Density 0.018%

mentions of gender, specifically focusing on males

mentions of the word "male."

No Comments

No Known Activations