INDEX

Explanations

terms related to historical events, particularly significant world wars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 vendeurs

-0.46

LogFactory

-0.43

 hini

-0.43

 Hivatalos

-0.42

cipline

-0.42

 AttributeSet

-0.41

UserScript

-0.40

 llorando

-0.38

 doanh

-0.37

 otak

-0.37

POSITIVE LOGITS

war

1.60

 WWII

1.39

War

1.38

 wars

1.37

War

1.21

 World

1.19

war

1.19

 guerra

1.19

WW

1.18

 guerre

1.16

Activations Density 0.283%

terms related to historical events, particularly significant world wars

No Comments

No Known Activations