INDEX

Explanations

references to privacy and related concepts in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 auroit

-0.49

 camisetas

-0.41

 Pemain

-0.39

 enfans

-0.39

 aulas

-0.38

 założ

-0.38

 avoient

-0.37

 sidang

-0.37

 Consejos

-0.37

 lujo

-0.37

POSITIVE LOGITS

 kasarigan

0.79

 lenker

0.75

<?

0.74

ніципалі

0.70

 Administrativna

0.69

 GenerationType

0.68

 betweenstory

0.68

 ivelany

0.67

GEBURTSDATUM

0.67

parsedMessage

0.67

Activations Density 0.193%

references to privacy and related concepts in the text

No Comments

No Known Activations