INDEX

Explanations

class definitions and their access modifiers in programming code

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

public class

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

 betweenstory

-0.40

 forfait

-0.40

 Wagen

-0.40

 Geschw

-0.39

 yoktur

-0.36

Caratter

-0.35

wußt

-0.35

 riqueza

-0.35

 Gästen

-0.35

 enfans

-0.35

POSITIVE LOGITS

protoimpl

0.62

 ujednoznacz

0.55

Geplaatst

0.54

XmlRootElement

0.54

 мәкалә

0.54

المناصب

0.53

Билгалдахарш

0.52

OGND

0.52

/*

0.52

StoreMessageInfo

0.50

Activations Density 0.002%

class definitions and their access modifiers in programming code

public class

No Comments

No Known Activations