INDEX

Explanations

words related to danger or potential harm

oai_token-act-pair · gpt-3.5-turbo

references to danger or harmful situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

issance

-0.81

ļéĨĴ

-0.78

galitarian

-0.73

guyen

-0.73

ergy

-0.71

owned

-0.71

Ħ¢

-0.70

elle

-0.70

urally

-0.69

eenth

-0.68

POSITIVE LOGITS

danger

0.95

 Danger

0.91

 endanger

0.82

 danger

0.82

ously

0.82

 dangers

0.81

lur

0.81

 lurking

0.78

 dangerous

0.74

 peril

0.73

Activations Density 0.054%

words related to danger or potential harm

references to danger or harmful situations

No Comments

No Known Activations