INDEX

Explanations

references to processes and actions involved in record management or data handling

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

measurement and technical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PRNewswire

-0.53

HtmlAttribute

-0.51

OrNil

-0.50

fxml

-0.47

WebElementEntity

-0.46

oa̍t

-0.46

TypedDataSet

-0.44

DTOs

-0.44

orry

-0.43

)}}{

-0.43

POSITIVE LOGITS

oredCriteria

0.55

matchCondition

0.54

tagext

0.46

ftagPool

0.44

 femininas

0.43

 JpaRepository

0.39

Портали

0.38

belajaran

0.37

 queſta

0.37

 kaynağından

0.36

Activations Density 0.287%

references to processes and actions involved in record management or data handling

measurement and technical terms

No Comments

No Known Activations