INDEX

Explanations

References to GDP (Gross Domestic Product) figures

oai_token-act-pair · gpt-3.5-turbo

references to Gross Domestic Product (GDP) and its related metrics

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

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.74

Jem

-0.73

opol

-0.71

ogyn

-0.70

WARE

-0.68

geon

-0.67

drug

-0.67

soDeliveryDate

-0.66

 Coulter

-0.62

Wem

-0.61

POSITIVE LOGITS

 growth

0.81

GDP

0.81

 expenditure

0.80

Stats

0.78

 Growth

0.76

 multiplier

0.75

iets

0.75

ilion

0.73

rowth

0.73

 measurement

0.70

Activations Density 0.025%

References to GDP (Gross Domestic Product) figures

references to Gross Domestic Product (GDP) and its related metrics

No Comments

No Known Activations