INDEX

Explanations

phrases related to legal actions or criminal activities

oai_token-act-pair · gpt-3.5-turbo

actions related to criminal activity or legal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

endif

-0.79

DragonMagazine

-0.74

isSpecialOrderable

-0.73

oÄŁ

-0.72

faced

-0.69

Coming

-0.69

chance

-0.67

Acknowled

-0.67

ciating

-0.66

dding

-0.65

POSITIVE LOGITS

 illegally

1.07

 unlawfully

1.06

 improperly

1.00

 illegal

0.99

 underage

0.99

 unlawful

0.96

 indecent

0.95

 improper

0.94

 unauthorized

0.86

 stolen

0.86

Activations Density 0.311%

phrases related to legal actions or criminal activities

actions related to criminal activity or legal issues

No Comments

No Known Activations