INDEX

Explanations

references to historical wars, especially World War II

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

IVEREF

-0.77

Geplaatst

-0.74

Hauptartikel

-0.74

Jegyzetek

-0.67

 дописавши

-0.66

 Ressources

-0.66

})->

-0.65

contentLoaded

-0.64

rceil

-0.64

 illustrazione

-0.62

POSITIVE LOGITS

 WWII

1.15

war

0.89

 Weltkrieg

0.89

 wartime

0.86

War

0.85

大戦

0.77

 Hitler

0.74

War

0.72

 Nazi

0.70

 Holocaust

0.70

Activations Density 0.211%

references to historical wars, especially World War II

No Comments

No Known Activations