INDEX

Explanations

discriminatory language related to race, gender, sexual orientation, and religion

oai_token-act-pair · gpt-3.5-turbo

instances of discriminatory language or terms related to prejudice and bigotry

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hower

-0.87

leaf

-0.82

pletion

-0.79

flix

-0.77

change

-0.76

pring

-0.75

ources

-0.75

imum

-0.75

ership

-0.73

aper

-0.72

POSITIVE LOGITS

 slurs

1.48

 stereotypes

1.02

 prejudice

1.00

 jokes

0.99

 homophobic

0.97

tir

0.96

 slur

0.96

 bigot

0.95

 sexist

0.94

 prejud

0.94

Activations Density 0.077%

discriminatory language related to race, gender, sexual orientation, and religion

instances of discriminatory language or terms related to prejudice and bigotry

No Comments

No Known Activations