INDEX

Explanations

references to the variable 'P', potentially denoting significant entities or variables in a mathematical or statistical context

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

Appears before references or citations

np_acts-logits-general · gemini-2.0-flash

initials and proper nouns

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

xda

-0.47

ッズ

-0.44

thalten

-0.44

eapple

-0.43

 vocales

-0.42

 Guts

-0.42

どころ

-0.42

culus

-0.41

 Vuelta

-0.41

islative

-0.40

POSITIVE LOGITS

oredCriteria

0.84

ValueStyle

0.82

parsedMessage

0.78

RenderAtEndOf

0.74

yntaxException

0.72

ThroughAttribute

0.71

addCriterion

0.70

didSet

0.69

出版年

0.68

 mergeFrom

0.67

Activations Density 0.233%

references to the variable 'P', potentially denoting significant entities or variables in a mathematical or statistical context

Appears before references or citations

initials and proper nouns

No Comments

No Known Activations