INDEX

Explanations

word sequences related to harassment, discrimination, abuse, violence and assault

oai_token-act-pair · gpt-3.5-turbo

references to harassment, violence, and related abuses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

liam

-0.78

 Bucket

-0.77

DragonMagazine

-0.74

 Tycoon

-0.74

Legendary

-0.71

ernels

-0.71

 Compact

-0.71

*/(

-0.69

natureconservancy

-0.68

phalt

-0.67

POSITIVE LOGITS

 intimidation

1.63

 harassment

1.52

 retaliation

1.49

 bullying

1.43

 discrimination

1.42

 coercion

1.36

 harassing

1.34

 unwelcome

1.31

 derogatory

1.31

 threats

1.27

Activations Density 0.322%

word sequences related to harassment, discrimination, abuse, violence and assault

references to harassment, violence, and related abuses

No Comments

No Known Activations