INDEX

Explanations

words related to threats or harm

oai_token-act-pair · gpt-3.5-turbo

phrases indicating potential threats or harm to individuals or society

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

soDeliveryDate

-0.89

ihad

-0.71

arten

-0.70

tions

-0.67

need

-0.66

anooga

-0.63

sponsored

-0.62

iHUD

-0.61

 Cosponsors

-0.60

hent

-0.60

POSITIVE LOGITS

 injure

0.86

adies

0.78

 ensure

0.76

 compensate

0.76

 avoid

0.75

asted

0.75

 assist

0.74

 enhance

0.74

 reduce

0.74

 achieve

0.73

Activations Density 0.167%

words related to threats or harm

phrases indicating potential threats or harm to individuals or society

No Comments

No Known Activations