INDEX

Explanations

documentation-related phrases and annotations in programming code

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

Code comments/documentation markers

np_acts-logits-general · gemini-2.0-flash

documentation tags like @return or @param

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IsContent

-0.67

parsedMessage

-0.61

afficheront

-0.58

GraphicsUnit

-0.54

oredCriteria

-0.53

OGND

-0.53

ніципалі

-0.52

 SwitchCompat

-0.52

CloseOperation

-0.51

 Италијани

-0.51

POSITIVE LOGITS

 ModelExpression

0.47

propTypes

0.44

 cref

0.42

="@+

0.42

 kasarigan

0.39

XmlAccessorType

0.37

Personendaten

0.36

RuleContext

0.35

Predecesor

0.35

ngdoc

0.34

Activations Density 0.195%

documentation-related phrases and annotations in programming code

Code comments/documentation markers

documentation tags like @return or @param

No Comments

No Known Activations