INDEX

Explanations

phrases related to the Tour de France

oai_token-act-pair · gpt-3.5-turbo

mentions of the Tour de France and its variations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 teasp

-0.86

mble

-0.79

aceous

-0.77

soever

-0.75

DragonMagazine

-0.75

omsky

-0.75

regor

-0.73

orrow

-0.72

onom

-0.71

raints

-0.71

POSITIVE LOGITS

la

0.97

los

0.95

las

0.82

Seg

0.81

 Excellence

0.78

utsche

0.78

 Vill

0.77

 Sant

0.76

Val

0.75

Jiu

0.75

Activations Density 0.038%

phrases related to the Tour de France

mentions of the Tour de France and its variations

No Comments

No Known Activations