INDEX

Explanations

references to locations and institutions within research contexts

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

Country or location names

np_acts-logits-general · gemini-2.0-flash

countries and regions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 Florentine

-0.62

 Frankfurter

-0.59

 Berliner

-0.58

ighborhood

-0.58

 barcel

-0.56

 Athenian

-0.55

tvguidetime

-0.54

ثيق

-0.53

 Etrus

-0.53

AnchorStyles

-0.52

POSITIVE LOGITS

 India

1.88

 Canada

1.79

 Australia

1.77

 Italy

1.72

 France

1.67

 Germany

1.64

 Ireland

1.63

 Spain

1.56

 Japan

1.56

 Nigeria

1.52

Activations Density 1.368%

references to locations and institutions within research contexts

Country or location names

countries and regions

No Comments

No Known Activations