INDEX

Explanations

corporate and organization-related terms or names

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

ScopeManager

-0.93

 ModelExpression

-0.79

Vidite

-0.71

-0.69

 PeEnEo

-0.67

StoryboardSegue

-0.66

aarrggbb

-0.66

Démographie

-0.65

Aiheesta

-0.63

Espèce

-0.63

POSITIVE LOGITS

XmlAccessType

0.47

 espar

0.46

 dessen

0.46

Obrázky

0.44

aco

0.44

elin

0.43

abara

0.42

ッズ

0.41

 détour

0.40

elsch

0.40

Activations Density 0.360%

corporate and organization-related terms or names

No Comments

No Known Activations