INDEX

Explanations

terminology related to data partitioning and processing in distributed computing

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

programming data processing

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

ScopeManager

-0.46

ьаж

-0.46

 AssemblyTitle

-0.41

loài

-0.40

ījum

-0.39

AndroidJUnit

-0.38

Kjelder

-0.37

adaptiveStyles

-0.37

 typelib

-0.36

mainAxisSize

-0.36

POSITIVE LOGITS

 CreateTagHelper

0.52

SequentialGroup

0.46

RenderAtEndOf

0.45

WriteTagHelper

0.45

tilhe

0.43

 pamięci

0.42

 TableColumn

0.40

InputTagHelper

0.40

ChildScrollView

0.40

 Exercise

0.40

Activations Density 0.038%

terminology related to data partitioning and processing in distributed computing

programming data processing

No Comments

No Known Activations