INDEX

Explanations

phrases focusing on past experiences and reflections on previous content

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

Referring to previous articles or blog posts

np_acts-logits-general · gemini-2.0-flash

referring to articles/blogs

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 للاسماء

-0.59

 HasFactory

-0.57

Према

-0.55

 चुनें

-0.50

 opérés

-0.50

الإنجليزية

-0.49

UrlResolution

-0.48

bootstrapcdn

-0.47

setCellValue

-0.47

PointerException

-0.47

POSITIVE LOGITS

 article

2.48

 articles

2.19

 blog

2.15

article

2.00

 Article

1.81

Article

1.78

 blogs

1.78

 artikel

1.72

articles

1.72

blog

1.70

Activations Density 0.523%

phrases focusing on past experiences and reflections on previous content

Referring to previous articles or blog posts

referring to articles/blogs

No Comments

No Known Activations