INDEX

Explanations

copyright information related to images

oai_token-act-pair · gpt-3.5-turbo

mentions of news organizations or media outlets

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 amendments

-0.72

 SHALL

-0.69

 treason

-0.63

 heresy

-0.62

rous

-0.62

 includ

-0.61

 affirmative

-0.59

viol

-0.59

yea

-0.59

 admon

-0.58

POSITIVE LOGITS

allery

0.95

 Shutterstock

0.90

photos

0.87

 Images

0.84

 Photos

0.79

 Image

0.78

Images

0.78

Ãį

0.74

 Palest

0.73

 Photography

0.73

Activations Density 0.045%

copyright information related to images

mentions of news organizations or media outlets

No Comments

No Known Activations