INDEX

Explanations

mentions of comparative statements involving countries or states

oai_token-act-pair · gpt-3.5-turbo

comparative statements regarding country-specific issues and challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 Pepe

-0.74

 Alchemist

-0.74

 alias

-0.72

 Pupp

-0.71

Sgt

-0.68

 Fenrir

-0.68

 Levine

-0.67

 Reincarn

-0.67

 Priest

-0.67

 Edwin

-0.66

POSITIVE LOGITS

 countries

2.02

 nations

1.86

 Countries

1.71

 democracies

1.54

 industrialized

1.50

 jurisdictions

1.45

 country

1.43

 nation

1.42

 provinces

1.41

 States

1.37

Activations Density 0.397%

mentions of comparative statements involving countries or states

comparative statements regarding country-specific issues and challenges

No Comments

No Known Activations