INDEX

Explanations

contextual introductory markers for articles or reports

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

Junk tokens and rare symbols

np_acts-logits-general · gemini-2.0-flash

solve math equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

าก็

-0.52

 Livraison

-0.49

jetty

-0.49

########.

-0.45

 OnClickListener

-0.45

phosa

-0.44

的山

-0.43

Magento

-0.43

 JURIS

-0.43

zzleHttp

-0.43

POSITIVE LOGITS

awtextra

1.13

Personensuche

0.99

 <<<<<<<<<<<<<<

0.94

IndentedString

0.94

:✨

0.94

دانشنامهٔ

0.92

0.90

 resourceCulture

0.88

ThroughAttribute

0.86

MemoryWarning

0.83

Activations Density 0.071%

contextual introductory markers for articles or reports

Junk tokens and rare symbols

solve math equations

No Comments

No Known Activations