INDEX

Explanations

terms and concepts related to software development frameworks and patterns, particularly in Java and Kotlin

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

Code related to repositories or data classes

np_acts-logits-general · gemini-2.0-flash

data classes and repositories

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 guider

-0.43

gées

-0.39

CGContext

-0.38

Становништво

-0.36

ImageField

-0.36

kannt

-0.36

xrTableCell

-0.36

pexpr

-0.35

fputs

-0.35

 promised

-0.35

POSITIVE LOGITS

ArgsConstructor

1.30

Data

0.92

Parcelize

0.82

dataclass

0.80

Getter

0.79

 dAtA

0.77

 Data

0.75

Setter

0.69

 autorytatywna

0.63

 viewDidLoad

0.63

Activations Density 0.106%

terms and concepts related to software development frameworks and patterns, particularly in Java and Kotlin

Code related to repositories or data classes

data classes and repositories

No Comments

No Known Activations