INDEX

Explanations

Java annotations and entity management concepts

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

Code, class names, and programming terms

np_acts-logits-general · gemini-2.0-flash

class names or homozygosity

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

pushFollow

-0.40

ftagPool

-0.39

 BigNumberish

-0.39

 Erfurt

-0.38

зер

-0.37

 TableColumn

-0.36

 fainted

-0.34

MultipartFile

-0.34

 Besucher

-0.34

Xna

-0.33

POSITIVE LOGITS

SpringBootTest

0.82

WebServlet

0.77

ControllerAdvice

0.67

 ProtoMessage

0.60

rungsseite

0.59

NgModule

0.59

 NgModule

0.58

RefNanny

0.58

 autorytatywna

0.57

 surla

0.57

Activations Density 0.032%

Java annotations and entity management concepts

Code, class names, and programming terms

class names or homozygosity

No Comments

No Known Activations