INDEX

Explanations

terms related to the LGBTQ+ community and issues around discrimination and support

oai_token-act-pair · gpt-3.5-turbo

references to the LGBTQ community 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

pmwiki

-0.83

ĳå£«

-0.78

æ©Ł

-0.73

 Closed

-0.70

 weighted

-0.68

 Wast

-0.67

nown

-0.66

 ACTIONS

-0.66

Completed

-0.64

Contents

-0.64

POSITIVE LOGITS

marriage

0.82

 lesbian

0.80

 Advocate

0.74

 lesbians

0.72

roups

0.70

iyah

0.68

iland

0.68

doms

0.67

bia

0.65

 empowerment

0.65

Activations Density 0.369%

terms related to the LGBTQ+ community and issues around discrimination and support

references to the LGBTQ community and related topics

No Comments

No Known Activations