INDEX

Explanations

references to specific countries, particularly those in Europe and Latin America

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

:✨

-0.76

rostis

-0.72

verwijspagina

-0.63

€.

-0.62

りの

-0.61

 Ennis

-0.61

namental

-0.59

=-=-=-=-

-0.58

inescent

-0.57

 Scenic

-0.57

POSITIVE LOGITS

 Russia

1.11

 Mexico

0.99

 France

0.98

 Japan

0.96

 India

0.94

 Egypt

0.94

 Germany

0.93

Russia

0.92

 America

0.91

 Argentina

0.89

Activations Density 0.217%

references to specific countries, particularly those in Europe and Latin America

No Comments

No Known Activations