INDEX

Explanations

locations mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

references to geographic locations, particularly within the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 plaque

-0.76

pmwiki

-0.74

DragonMagazine

-0.69

 derogatory

-0.67

 antit

-0.62

bum

-0.61

 malf

-0.61

 fuzz

-0.61

 advising

-0.60

 steering

-0.60

POSITIVE LOGITS

 territories

1.01

heastern

0.95

 Territories

0.95

 Emirates

0.94

 Netherlands

0.93

anmar

0.89

 continents

0.87

Spain

0.87

 Caucasus

0.86

England

0.86

Activations Density 0.327%

locations mentioned in news articles

references to geographic locations, particularly within the United States

No Comments

No Known Activations