INDEX

Explanations

phrases related to the functionality and status of devices, particularly focusing on operation, power, and states of use

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

Something is in an active state

np_acts-logits-general · gemini-2.0-flash

operational or active state

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.61

دانشنامهٔ

-0.59

FailureListener

-0.56

 dikirim

-0.55

 mutagenicity

-0.54

WebElementEntity

-0.54

GenerationType

-0.54

 Rigidbody

-0.52

حياته

-0.52

CloseOperation

-0.51

POSITIVE LOGITS

 operational

1.00

 functioning

0.95

 active

0.94

 functional

0.87

 running

0.86

 turned

0.85

 activated

0.84

 working

0.81

 engaged

0.81

 operating

0.80

Activations Density 0.424%

phrases related to the functionality and status of devices, particularly focusing on operation, power, and states of use

Something is in an active state

operational or active state

No Comments

No Known Activations