INDEX

Explanations

references to null checks and conditions in code

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

"null" (or NULL)

np_acts-logits-general · gemini-2.0-flash

checks for null or zero

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

LookAnd

-0.85

jsxFileName

-0.74

//

-0.72

++]=

-0.70

()];

-0.64

'],$

-0.63

RefNanny

-0.62

--)

-0.62

());//

-0.62

"]="

-0.62

POSITIVE LOGITS

 tarko

0.61

seamnă

0.56

exitRule

0.56

 Diallo

0.55

 rossa

0.54

 présentes

0.54

的情况下

0.53

OrWhiteSpace

0.52

 amarillas

0.52

&&

0.51

Activations Density 0.070%

references to null checks and conditions in code

"null" (or NULL)

checks for null or zero

No Comments

No Known Activations