INDEX

Explanations

expressions related to language proficiency and multilingualism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 poffible

-0.67

VersionUID

-0.67

 Lightboxes

-0.66

 myſelf

-0.66

 allegorical

-0.65

 difp

-0.65

 Monfieur

-0.65

 Majefty

-0.63

 fubject

-0.63

 Scul

-0.62

POSITIVE LOGITS

 languages

0.77

 language

0.74

Languages

0.73

olingo

0.67

 Language

0.66

language

0.66

Language

0.63

languages

0.62

 fluent

0.60

fluent

0.59

Activations Density 0.246%

expressions related to language proficiency and multilingualism

No Comments

No Known Activations