INDEX

Explanations

concepts related to gender

oai_token-act-pair · gpt-3.5-turbo

terms related to gender identity and gender disparities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

BLIC

-0.75

iries

-0.72

Gi

-0.71

ernels

-0.71

ournal

-0.68

Mub

-0.68

Interstitial

-0.68

 Warrant

-0.67

amina

-0.67

 Gerr

-0.67

POSITIVE LOGITS

 dysph

1.06

 Equality

0.95

 pronouns

0.93

 equality

0.92

 stereotypes

0.88

bender

0.86

 identity

0.85

bent

0.84

bending

0.84

fuck

0.83

Activations Density 0.030%

concepts related to gender

terms related to gender identity and gender disparities

No Comments

No Known Activations