INDEX

Explanations

keywords related to programming and class declarations, particularly in Java

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

"public" keyword in code

np_acts-logits-general · gemini-2.0-flash

public static class

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

unknownFields

-0.62

⟬

-0.57

 venuto

-0.54

yntaxException

-0.54

webElementGuid

-0.54

 būtų

-0.53

GNUC

-0.52

 dépasser

-0.52

typeof

-0.52

исленность

-0.51

POSITIVE LOGITS

 static

0.57

 للمعارف

0.57

 class

0.56

 rowspan

0.56

IVEREF

0.53

 Nella

0.52

!*\

0.51

class

0.47

igshid

0.46

fjspx

0.45

Activations Density 0.047%

keywords related to programming and class declarations, particularly in Java

"public" keyword in code

public static class

No Comments

No Known Activations