INDEX

Explanations

terms related to racial identity and discrimination

oai_token-act-pair · gpt-3.5-turbo

topics related to race and ethnicity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

erva

-0.84

unction

-0.78

UNE

-0.77

cit

-0.76

irs

-0.75

uden

-0.74

ushima

-0.74

orage

-0.74

Mub

-0.74

unker

-0.73

POSITIVE LOGITS

course

1.03

 Equality

0.86

horse

0.81

blind

0.78

 slurs

0.78

 prejudice

0.77

bending

0.76

hair

0.76

 Discrimination

0.75

 relations

0.74

Activations Density 0.018%

terms related to racial identity and discrimination

topics related to race and ethnicity

No Comments

No Known Activations