INDEX

Explanations

French words, likely related to wine

oai_token-act-pair · gpt-3.5-turbo

words related to wine or wine regions

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

itans

-0.87

 redistributed

-0.86

ageddon

-0.81

avin

-0.77

urtle

-0.77

okin

-0.75

anmar

-0.75

berra

-0.73

nton

-0.72

omaly

-0.72

POSITIVE LOGITS

 Lauder

0.94

 Royale

0.87

lÃ©

0.86

 Ãł

0.83

 Denis

0.75

naire

0.75

 dÃ©

0.73

du

0.73

 Ã©

0.72

Rou

0.72

Activations Density 0.022%

French words, likely related to wine

words related to wine or wine regions

No Comments

No Known Activations