INDEX

Explanations

different sections or segments in a structured text or data format

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 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

uxxxx

-0.69

RegressionTest

-0.67

Географиясе

-0.64

adaptiveStyles

-0.61

IndentedString

-0.58

contentLoaded

-0.57

PreferredItem

-0.56

RotationOrder

-0.56

 CreateTagHelper

-0.56

 createSprite

-0.55

POSITIVE LOGITS

 Gegenteil

0.44

 comunión

0.42

Atentamente

0.42

 Sortiment

0.42

 Voraus

0.40

 Lingkungan

0.40

AMIENTO

0.40

 Utama

0.39

 Anbau

0.39

 Privacidad

0.39

Activations Density 0.481%

different sections or segments in a structured text or data format

No Comments

No Known Activations