INDEX

Explanations

technical terms and keywords related to programming and software development

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

EncodedLen

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

addContainerGap

-0.60

MemoryWarning

-0.58

InitStruct

-0.55

AccessorTable

-0.54

migrationBuilder

-0.50

CloseOperation

-0.50

endregion

-0.50

argout

-0.49

AutoModerator

-0.49

 companyId

-0.47

POSITIVE LOGITS

 الرياضيه

0.43

 filled

0.40

figcaption

0.39

 actionMode

0.37

filled

0.37

SNA

0.36

nœ

0.36

strict

0.36

IPA

0.35

Filled

0.35

Activations Density 0.106%

technical terms and keywords related to programming and software development

EncodedLen

No Comments

No Known Activations