INDEX

Explanations

references to historical events and figures

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

World War I era

np_acts-logits-general · gemini-2.0-flash

years and dates

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

WebElementEntity

-0.70

IContainer

-0.65

Espèce

-0.64

 insuffisamment

-0.64

RenderAtEndOf

-0.62

KGB

-0.60

TV

-0.60

 télévision

-0.59

BagLayout

-0.58

 Fernsehen

-0.57

POSITIVE LOGITS

WWI

0.71

 silent

0.51

 First

0.51

ppelin

0.50

第一次

0.49

Personendaten

0.48

'}),

0.48

انجليز

0.48

 referenties

0.48

 Ersten

0.47

Activations Density 0.358%

references to historical events and figures

World War I era

years and dates

No Comments

No Known Activations