INDEX

Explanations

assignment and comparison operations in code

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

"for (var i =" loops

np_acts-logits-general · gemini-2.0-flash

loop index initialization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 CanadaChoose

-0.68

 Italijanski

-0.66

WebElementEntity

-0.65

OGND

-0.65

 незавершена

-0.62

oredCriteria

-0.61

onedDateTime

-0.61

 otomatig

-0.59

 imageNamed

-0.59

ⓧ

-0.58

POSITIVE LOGITS

counter

0.33

{};

0.32

 ranging

0.31

COUNTER

0.30

Counter

0.29

 Papst

0.28

TabIndex

0.27

 usah

0.27

 başına

0.26

 counter

0.26

Activations Density 0.214%

assignment and comparison operations in code

"for (var i =" loops

loop index initialization

No Comments

No Known Activations