INDEX

Explanations

references to race

oai_token-act-pair · gpt-3.5-turbo

references to race and related concepts

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

cit

-0.80

UNE

-0.79

erva

-0.75

irs

-0.74

anmar

-0.73

orage

-0.72

hiba

-0.71

unction

-0.71

ickson

-0.70

psons

-0.70

POSITIVE LOGITS

course

0.91

 Equality

0.88

blind

0.87

 prejudice

0.83

 slurs

0.82

 supremacy

0.82

 relations

0.82

 Discrimination

0.81

bending

0.76

 purity

0.75

Activations Density 0.029%

references to race

references to race and related concepts

No Comments

No Known Activations