INDEX

Explanations

mathematical notation and expressions related to structures and properties in algebra or geometry

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

mathematical expressions with `mathfrak`

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 pageContext

-0.28

才是

-0.25

 useDispatch

-0.25

 Gallimard

-0.24

 nuage

-0.24

 TextEditing

-0.24

WebpackPlugin

-0.24

 armed

-0.23

 SafeMath

-0.22

 secours

-0.22

POSITIVE LOGITS

 ویکی‌پدی

0.91

 Biôgrafia

0.88

 autorytatywna

0.84

SharedCtor

0.82

parsedMessage

0.80

Cyfarwyddwr

0.79

 transfieras

0.78

 Taktlose

0.73

 Paglinawan

0.72

ロウィン

0.71

Activations Density 2.945%

mathematical notation and expressions related to structures and properties in algebra or geometry

mathematical expressions with `mathfrak`

No Comments

No Known Activations