INDEX

Explanations

references to Asia in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 مرئيه

-0.85

 للاسماء

-0.80

NameInMap

-0.70

 насеље

-0.69

 policiales

-0.68

alyptus

-0.68

Билгалдахарш

-0.67

 kasarigan

-0.67

loroethene

-0.67

SourceChecksum

-0.65

POSITIVE LOGITS

 Asia

1.83

Asia

1.65

 Asian

1.59

 asia

1.52

 ASIA

1.49

 Asians

1.46

Asian

1.39

ASIA

1.33

 asian

1.28

 Asie

1.24

Activations Density 0.043%

references to Asia in various contexts

No Comments

No Known Activations