INDEX

Explanations

references to political concepts and terminology

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

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

makeConstraints

-0.64

Tikang

-0.52

 Américas

-0.52

 aanbod

-0.49

 noastră

-0.48

 cref

-0.48

 Crew

-0.47

 jScrollPane

-0.46

̈́

-0.45

EndInit

-0.45

POSITIVE LOGITS

 POLITICAL

0.85

 political

0.83

 politics

0.81

political

0.81

Political

0.79

 Political

0.76

 politic

0.72

 POLITICS

0.71

politics

0.70

 Politics

0.68

Activations Density 0.013%

references to political concepts and terminology

No Comments

No Known Activations