INDEX

Explanations

phrases related to news agencies and political events

oai_token-act-pair · gpt-3.5-turbo

references to 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

 foreclosure

-0.78

weed

-0.77

 sucker

-0.70

 Confederate

-0.70

 trout

-0.69

 Arkham

-0.69

 Yosemite

-0.69

 ______

-0.69

 lumber

-0.67

worms

-0.67

POSITIVE LOGITS

inational

0.92

 Ankara

0.87

Asia

0.85

Euro

0.83

 Foreign

0.82

 Azerbai

0.82

 Lavrov

0.81

 Malta

0.80

News

0.80

Syria

0.78

Activations Density 0.709%

phrases related to news agencies and political events

references to news organizations or media outlets

No Comments

No Known Activations