INDEX

Explanations

words related to danger or hazardous situations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "dangerous" used in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

elf

-0.80

innie

-0.78

rix

-0.76

ļéĨĴ

-0.75

roma

-0.75

anish

-0.75

via

-0.74

elle

-0.74

angular

-0.73

arger

-0.73

POSITIVE LOGITS

 dangerous

0.95

 undermin

0.92

 endanger

0.91

 adolesc

0.89

 danger

0.80

 mischief

0.79

 sounding

0.79

danger

0.77

 dangers

0.76

 libel

0.75

Activations Density 0.017%

words related to danger or hazardous situations

instances of the word "dangerous" used in various contexts

No Comments

No Known Activations