INDEX

Explanations

terms related to African-American identity and community

oai_token-act-pair · gpt-3.5-turbo

references to the African American population and related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Dickinson

-0.86

pload

-0.79

orious

-0.74

earch

-0.71

igslist

-0.70

 Shutterstock

-0.69

atche

-0.68

 Carly

-0.67

 Pastebin

-0.65

orem

-0.65

POSITIVE LOGITS

based

1.10

American

1.08

themed

1.07

Americans

1.06

style

1.03

inspired

1.01

induced

0.98

related

0.95

controlled

0.95

origin

0.93

Activations Density 0.080%

terms related to African-American identity and community

references to the African American population and related topics

No Comments

No Known Activations