INDEX

Explanations

discussions about political norms and behaviors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

énario

-0.57

migrationBuilder

-0.56

principalColumn

-0.53

انجليز

-0.51

adə

-0.51

marshaller

-0.50

netbeans

-0.47

 cientí

-0.46

SearchTree

-0.46

 mystère

-0.45

POSITIVE LOGITS

 political

2.16

political

1.85

 Political

1.83

Political

1.78

 politics

1.72

 politically

1.70

 POLITICAL

1.67

 politici

1.57

 politische

1.49

 politic

1.48

Activations Density 0.541%

discussions about political norms and behaviors

No Comments

No Known Activations