INDEX

Explanations

instances of the concept of wrapping or enclosing something

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

"wrap" or its variations

np_acts-logits-general · gemini-2.0-flash

wrapping around

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

RegistryLite

-0.75

 Sinter

-0.69

fares

-0.67

addCriterion

-0.67

 AssemblyCulture

-0.66

RegressionTest

-0.65

 <=",

-0.65

MLLoader

-0.65

NBS

-0.64

SRC

-0.63

POSITIVE LOGITS

 wrap

1.63

 wraps

1.50

 wrapped

1.49

 wrapping

1.43

 Wrap

1.41

wrap

1.29

Wrap

1.28

wrapped

1.28

Wra

1.28

 Wrapping

1.27

Activations Density 0.102%

instances of the concept of wrapping or enclosing something

"wrap" or its variations

wrapping around

No Comments

No Known Activations