INDEX

Explanations

references to historical figures, specifically saints and their contributions

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

preceding names or titles

np_acts-logits-general · gemini-2.0-flash

religious and historical figures

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

AsUp

-0.72

enumi

-0.70

 Audiodateien

-0.67

dersfield

-0.54

 MotionEvent

-0.53

 KeyError

-0.53

 AppComponent

-0.53

Kariera

-0.50

/***/

-0.50

 crossorigin

-0.49

POSITIVE LOGITS

UseVisualStyle

0.64

ValueStyle

0.64

 Cyril

0.63

 Patriarch

0.63

 ModelExpression

0.62

Cop

0.60

 Byzantine

0.58

 bishop

0.58

 Orthodox

0.58

 métro

0.58

Activations Density 0.158%

references to historical figures, specifically saints and their contributions

preceding names or titles

religious and historical figures

No Comments

No Known Activations