INDEX

Explanations

references to data partitioning techniques in distributed systems

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

partitioning schemes

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

 Gegenwart

-0.32

">//

-0.31

 hins

-0.28

 aank

-0.27

 party

-0.27

="@+

-0.27

Disappear

-0.26

AddHtmlAttribute

-0.26

 circo

-0.26

 democrática

-0.26

POSITIVE LOGITS

elemField

0.67

MENAFN

0.62

BagConstraints

0.58

astéroïdes

0.58

uzz

0.57

 territorial

0.56

Bots

0.56

 Incl

0.54

ikusbot

0.54

 Coverage

0.54

Activations Density 0.090%

references to data partitioning techniques in distributed systems

partitioning schemes

No Comments

No Known Activations