INDEX

Explanations

mentions of militant groups and organizations

oai_token-act-pair · gpt-3.5-turbo

references to militant and insurgent groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 cones

-0.73

iture

-0.71

olor

-0.71

 impressions

-0.70

bugs

-0.69

Â¢

-0.69

 Guests

-0.69

Elsa

-0.69

airs

-0.69

ices

-0.68

POSITIVE LOGITS

 militant

3.27

 extremist

1.88

 separatist

1.72

 insurgent

1.71

 jihadist

1.60

 milit

1.57

 radical

1.54

radical

1.45

 terrorist

1.42

 fundamentalist

1.41

Activations Density 0.010%

mentions of militant groups and organizations

references to militant and insurgent groups

No Comments

No Known Activations