INDEX

Explanations

articles and quantifiers in the text

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

"a" followed by a noun

np_acts-logits-general · gemini-2.0-flash

a followed by something

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

 يتيمه

-1.00

 समीक्षाओं

-0.90

XmlAccessorType

-0.87

 للمعارف

-0.86

IntoConstraints

-0.83

OGND

-0.81

 geslacht

-0.79

Vidite

-0.78

 дописавши

-0.78

Datuak

-0.72

POSITIVE LOGITS

0.64

 wide

0.60

 unique

0.57

 history

0.53

 large

0.52

README

0.48

History

0.47

 History

0.47

mix

0.46

 focus

0.46

Activations Density 0.263%

articles and quantifiers in the text

"a" followed by a noun

a followed by something

No Comments

No Known Activations