INDEX

Explanations

terms and concepts related to mathematical structures and functions, particularly in linear algebra and complex analysis

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

matrix, operator, space, map

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

 pinulongan

-0.49

GraphicsUnit

-0.47

HasKey

-0.40

getColumnIndex

-0.38

 zukünf

-0.38

__(/*!

-0.37

ValueStyle

-0.37

shadowOpacity

-0.36

 exitosa

-0.36

POSITIVE LOGITS

 surla

0.60

 utafitiHapana

0.53

SequentialGroup

0.52

 estekak

0.49

IVEREF

0.48

IUrlHelper

0.47

usermodel

0.45

createServer

0.44

RegressionTest

0.41

yyj

0.40

Activations Density 0.211%

terms and concepts related to mathematical structures and functions, particularly in linear algebra and complex analysis

matrix, operator, space, map

No Comments

No Known Activations