INDEX

Explanations

references to the United States

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

기를

-0.61

djangoproject

-0.58

hå

-0.58

 turning

-0.53

AutoField

-0.53

โน

-0.52

Geo

-0.52

гл

-0.52

 colspan

-0.51

hint

-0.51

POSITIVE LOGITS

USA

2.04

USA

1.76

Usa

1.26

usa

1.22

Usa

0.99

 myſelf

0.98

 USSR

0.95

 Philippines

0.94

usa

0.92

Personensuche

0.90

Activations Density 0.068%

references to the United States

No Comments

No Known Activations