INDEX

Explanations

explicit mentions of racism

oai_token-act-pair · gpt-3.5-turbo

terms related to racism and accusations of racist behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ITNESS

-0.88

pad

-0.83

icular

-0.78

amina

-0.77

earchers

-0.71

ATURE

-0.71

arios

-0.71

Delivery

-0.71

itness

-0.69

stantial

-0.69

POSITIVE LOGITS

 slurs

1.27

 prejudice

1.02

 bigot

0.96

tir

0.96

 slur

0.93

 racists

0.92

 hatred

0.92

 racist

0.91

 stereotyp

0.91

 stereotypes

0.91

Activations Density 0.047%

explicit mentions of racism

terms related to racism and accusations of racist behavior

No Comments

No Known Activations