INDEX

Explanations

references to Italy and the Italian culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.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

</blockquote>

-0.68

がり

-0.63

cientos

-0.62

 McFadden

-0.61

 ве

-0.60

ghold

-0.60

 albero

-0.59

unci

-0.59

SharedCtor

-0.59

cloudf

-0.59

POSITIVE LOGITS

 Italy

1.15

 Italians

1.08

Italy

1.07

 Ital

1.01

 italy

1.01

Italie

0.98

Ita

0.96

 ITALY

0.95

 Italie

0.91

 ITAL

0.91

Activations Density 0.007%

references to Italy and the Italian culture

No Comments

No Known Activations