INDEX

Explanations

words related to social and racial segregation

oai_token-act-pair · gpt-3.5-turbo

terms and concepts related to racial segregation and inequality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

sonian

-0.74

Downloadha

-0.72

GH

-0.72

xxxxxxxx

-0.71

OD

-0.71

amina

-0.69

kj

-0.67

ulz

-0.65

ODUCT

-0.64

annis

-0.64

POSITIVE LOGITS

gregation

1.40

 segregation

1.26

 segreg

1.14

 segregated

1.05

pling

0.96

regation

0.81

pees

0.81

ipation

0.80

iple

0.79

plings

0.78

Activations Density 0.013%

words related to social and racial segregation

terms and concepts related to racial segregation and inequality

No Comments

No Known Activations