INDEX

Explanations

terms associated with programming language syntax, particularly variable declarations and modifiers

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

`static` keyword

np_acts-logits-general · gemini-2.0-flash

static final

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

msgSender

-0.71

 <<<<<<<<<<<<<<

-0.70

енча

-0.67

oredCriteria

-0.65

aarrggbb

-0.65

fromnode

-0.64

RegressionTest

-0.63

GEBURTSDATUM

-0.61

Geplaatst

-0.60

 Bourgoin

-0.60

POSITIVE LOGITS

 static

0.59

แข

0.55

STATIC

0.55

 Stad

0.54

JvmStatic

0.52

 ujednoznacz

0.51

static

0.50

statics

0.50

静态

0.49

 Static

0.48

Activations Density 0.013%

terms associated with programming language syntax, particularly variable declarations and modifiers

`static` keyword

static final

No Comments

No Known Activations