INDEX

Explanations

elements related to software documentation, especially those that indicate package management and error handling in Java

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

Code, especially java-related

np_acts-logits-general · gemini-2.0-flash

Java code, packages, and libraries

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

+#+#

-0.85

 vulgaires

-0.83

AndEndTag

-0.82

 intptr

-0.71

 typelib

-0.70

ReusableCell

-0.67

tagHelperRunner

-0.66

 CreateTagHelper

-0.65

Tetapi

-0.61

 Autorizaciones

-0.60

POSITIVE LOGITS

Java

0.61

 Java

0.59

<tfoot>

0.56

 autorytatywna

0.55

 JAVA

0.53

Clazz

0.52

JNIEnv

0.52

JAVA

0.50

Controllo

0.50

 Betis

0.50

Activations Density 0.406%

elements related to software documentation, especially those that indicate package management and error handling in Java

Code, especially java-related

Java code, packages, and libraries

No Comments

No Known Activations