INDEX

Explanations

mathematical expressions and symbols related to set theory and topology

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

Mathematical symbols

np_acts-logits-general · gemini-2.0-flash

mathematical notation and concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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



-0.70

 tributaries

-0.57

QApplication

-0.56

 Thebes

-0.53

ISupport

-0.52

 applicability

-0.52

 flared

-0.51

 footnotes

-0.49

IANA

-0.49

 stoichio

-0.49

POSITIVE LOGITS

AndEndTag

0.70

 fréquent

0.63

 endblock

0.57

UnitTesting

0.56

hilangan

0.52

 element

0.51

 resourceCulture

0.51

ьаж

0.50

 CascadeType

0.50

awtextra

0.49

Activations Density 1.738%

mathematical expressions and symbols related to set theory and topology

Mathematical symbols

mathematical notation and concepts

No Comments

No Known Activations