INDEX

Explanations

items that represent equality or assignments in programming syntax

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

thenReturn

-0.58

EndInit

-0.53

rawDesc

-0.51

irn

-0.51

 saper

-0.51

Cours

-0.48

 cours

-0.48

صار

-0.47

 دیکھیے

-0.47

盆

-0.47

POSITIVE LOGITS

eader

0.71

 GenerationType

0.70

存于互联网档案馆

0.68

 ✭✭

0.65

idemia

0.64

 AssemblyTitle

0.62

 UserDao

0.61

 Dagger

0.60

medriver

0.60

 dagger

0.59

Activations Density 0.003%

items that represent equality or assignments in programming syntax

No Known Activations