INDEX

Explanations

mentions of adult content

oai_token-act-pair · gpt-3.5-turbo

references to adult pornography

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

å§«

-0.80

 MacArthur

-0.70

soType

-0.70

pring

-0.69

 defe

-0.67

wcs

-0.66

IELD

-0.65

 Bolton

-0.63

 Quin

-0.62

hips

-0.61

POSITIVE LOGITS

ographers

1.24

ographer

1.10

ography

1.01

ographically

0.97

hub

0.97

ographic

0.90

 pornography

0.86

stars

0.85

 Porn

0.84

OGR

0.84

Activations Density 0.031%

mentions of adult content

references to adult pornography

No Comments

No Known Activations