INDEX

Explanations

mathematical notations and expressions related to set theory

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

latex mathematical notation

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

</strong>

-0.59

-0.56

</em>

-0.47

-0.46

 assi

-0.42

Day

-0.42

createCell

-0.41

HasValue

-0.40

 colo

-0.40

 Abel

-0.40

POSITIVE LOGITS

${\

1.13

${\

1.12

>{@

0.74

 autorytatywna

0.74

 Geſ

0.71

 Geſch

0.70

 surla

0.69

({\

0.68

 zijne

0.66

 todella

0.65

Activations Density 0.045%

mathematical notations and expressions related to set theory

latex mathematical notation

No Comments

No Known Activations