INDEX

Explanations

references to instances and object-related terminology in programming context

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

UI elements and code initialization

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

 surla

-0.65

Chham

-0.64

tershire

-0.56

 мәкал

-0.55

 يتيمه

-0.55

FromArgb

-0.54

ISupport

-0.52

infan

-0.52

SequentialGroup

-0.52

ucket

-0.50

POSITIVE LOGITS

NewUrlParser

0.30

 pernas

0.29

 accordingly

0.29

 appareils

0.28

localPosition

0.28

 titulaire

0.27

UIColor

0.26

 pré

0.26

 juges

0.26

 gradually

0.26

Activations Density 0.003%

references to instances and object-related terminology in programming context

UI elements and code initialization

No Comments

No Known Activations