INDEX

Explanations

references to user interface components, particularly those related to the UIKit framework

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

UI control components

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

 disambiguazione

-0.79

//

-0.59

 Esposito

-0.57

Slf

-0.56

 Lindley

-0.52

存于互联网档案馆

-0.51

 Brenner

-0.51

 Longo

-0.50

 Gott

-0.49

PropertyChanging

-0.49

POSITIVE LOGITS

UIC

0.79

UIC

0.74

UIS

0.63

UIS

0.62

UIT

0.56

UIP

0.53

UIL

0.51

UIM

0.51

UID

0.50

UID

0.50

Activations Density 0.007%

references to user interface components, particularly those related to the UIKit framework

UI control components

No Comments

No Known Activations