INDEX

Explanations

indications of technology and design elements related to digital environments

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

that appear before technical terms/jargon

np_acts-logits-general · gemini-2.0-flash

conducted announcement affairs

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

exao

-0.44

 surla

-0.42

ValueGeneration

-0.42

onViewCreated

-0.41

Unnamed

-0.40

itinéraire

-0.40

GetEnumerator

-0.39

iomanip

-0.39

zegor

-0.39

 ब्रेकडाउन

-0.39

POSITIVE LOGITS

 JpaRepository

0.44

Jeografia

0.39

QMetaType

0.39

 backgrounds

0.37

kuuta

0.36

endaft

0.36

awtextra

0.36

addCriterion

0.34

Background

0.34

 ivelany

0.34

Activations Density 0.592%

indications of technology and design elements related to digital environments

that appear before technical terms/jargon

conducted announcement affairs

No Comments

No Known Activations