INDEX

Explanations

terms associated with legal competency and mental health evaluations

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

Not in Any Lists

No Comments

Negative Logits

rxjs

-0.74

-0.53

Rem

-0.52

 JADX

-0.49

Rem

-0.49

built

-0.47

Firebase

-0.47

原创

-0.47

 crackling

-0.47

кра

-0.46

POSITIVE LOGITS

 feroit

0.91

 pinulongan

0.84

MessageTagHelper

0.81

 auroit

0.79

rrggbb

0.78

 réfrig

0.77

 normaux

0.76

contentLoaded

0.75

 fermés

0.75

Legături

0.75

Activations Density 0.033%

terms associated with legal competency and mental health evaluations

No Comments

No Known Activations