INDEX

Explanations

references to countries and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

pom

-0.37

mod

-0.36

REC

-0.35

post

-0.35

cla

-0.35

cur

-0.35

 التن

-0.35

cla

-0.34

bar

-0.34

 post

-0.34

POSITIVE LOGITS

 Denmark

0.98

 Italy

0.96

 Germany

0.95

 France

0.94

 Australia

0.92

 Austria

0.92

 Switzerland

0.92

 Sweden

0.92

 Mexico

0.91

 Belgium

0.90

Activations Density 0.668%

references to countries and locations

No Comments

No Known Activations