INDEX

Explanations

emphasized points and noteworthy observations in discussions or arguments

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

importance or relevance

np_acts-logits-general · gemini-2.0-flash

introducing important points

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 autorytatywna

-0.99

 AssemblyTitle

-0.92

 initComponents

-0.84

parsedMessage

-0.83

verwijspagina

-0.83

 estekak

-0.83

forRoot

-0.81

featureID

-0.80

makeConstraints

-0.79

addCriterion

-0.79

POSITIVE LOGITS

 instructive

0.64

 perhaps

0.57

 observation

0.57

 caution

0.56

 noteworthy

0.56

perhaps

0.52

 pertinent

0.51

 pertin

0.51

 interesting

0.50

 worth

0.50

Activations Density 0.877%

emphasized points and noteworthy observations in discussions or arguments

importance or relevance

introducing important points

No Comments

No Known Activations