INDEX

Explanations

locations mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

conjunctions, specifically the word "and."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DragonMagazine

-0.89

utenberg

-0.77

Adapt

-0.70

flush

-0.66

 incent

-0.66

BIL

-0.64

material

-0.64

physical

-0.63

 distingu

-0.63

eton

-0.62

POSITIVE LOGITS

 elsewhere

1.00

ornia

0.96

 Papua

0.95

 Switzerland

0.87

 Mexico

0.87

 Wales

0.86

 southwestern

0.86

 abroad

0.86

 France

0.84

 vicinity

0.83

Activations Density 0.210%

locations mentioned in news articles

conjunctions, specifically the word "and."

No Comments

No Known Activations