INDEX

Explanations

technical terms and concepts related to software development and data processing

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

programming languages and libraries

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

setVerticalGroup

-0.69

LookAnd

-0.58

endregion

-0.57

SourceChecksum

-0.53

AntiForgeryToken

-0.52

 defaultstate

-0.49

RenderAtEndOf

-0.47

angliski

-0.46

addCriterion

-0.46

queryInterface

-0.45

POSITIVE LOGITS

IBarButtonItem

0.53

featureID

0.48

 мәкал

0.46

 mauva

0.46

enregist

0.45

dengar

0.44

tawesome

0.43

Radio

0.43

Cler

0.42

extField

0.42

Activations Density 0.002%

technical terms and concepts related to software development and data processing

programming languages and libraries

No Comments

No Known Activations