INDEX

Explanations

code structures and syntax related to the definition and initialization of variables in programming

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

The token "new"

np_acts-logits-general · gemini-2.0-flash

new object instantiation

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

oredCriteria

-0.49

 بيها

-0.46

 session

-0.44

rungsseite

-0.42

 betweenstory

-0.41

 Session

-0.41

Session

-0.41

 bête

-0.41

imath

-0.41

ліст

-0.40

POSITIVE LOGITS

 resourceCulture

0.70

lihood

0.65

assertArray

0.63

initializeApp

0.62

 通販

0.61

IonicModule

0.60

IsContent

0.60

StackNavigator

0.60

 Lordship

0.60

 arrayOf

0.60

Activations Density 0.460%

code structures and syntax related to the definition and initialization of variables in programming

The token "new"

new object instantiation

No Comments

No Known Activations