INDEX

Explanations

keywords and phrases related to programming, particularly in the context of Java, NUnit testing, and XHTML structure

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

<start_of_turn>user

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

requireNonNull

-0.47

ParallelGroup

-0.44

AppendLine

-0.35

łaszcza

-0.35

addComponent

-0.34

ագրություններ

-0.33

getStringExtra

-0.33

 günstiger

-0.33

 note

-0.33

cf

-0.33

POSITIVE LOGITS

JNI

1.26

UnitTesting

1.13

JNI

1.01

InstrumentedTest

0.98

 cellpadding

0.91

 disambiguazione

0.74

jni

0.73

 UIButton

0.72

NameInMap

0.72

 Biôgrafia

0.66

Activations Density 0.001%

keywords and phrases related to programming, particularly in the context of Java, NUnit testing, and XHTML structure

<start_of_turn>user

No Comments

No Known Activations