INDEX

Explanations

phrases related to programming and method definitions

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

visitor.visitSingular

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 HttpNotFound

-0.75

 autorytatywna

-0.74

:✨

-0.69

afficheront

-0.68

fromnode

-0.67

 Италијани

-0.67

 Biôgrafia

-0.66

windowFixed

-0.65

 wikipagina

-0.63

GEBURTSDATUM

-0.63

POSITIVE LOGITS

</>

0.51

ۦ

0.45

 ་་

0.44

 wireType

0.43

 Pockets

0.43

ۢ

0.43

뀔

0.42

 Paws

0.41

 Pocket

0.41

 Latitude

0.41

Activations Density 0.042%

phrases related to programming and method definitions

visitor.visitSingular

No Comments

No Known Activations