INDEX

Explanations

references to evidence and its qualities in a legal context

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

ertale

-0.90

Xna

-0.79

SBATCH

-0.79

ptonshire

-0.79

Wart

-0.77

 useRouter

-0.75

 useDispatch

-0.73

 >=",

-0.73

lidays

-0.71

Datuak

-0.70

POSITIVE LOGITS

evidence

1.94

 Evidence

1.90

 EVIDENCE

1.85

 evidence

1.84

Evidence

1.83

 evidences

1.55

 Evid

1.45

 evidencia

1.28

 preuves

1.21

 evid

1.20

Activations Density 0.124%

references to evidence and its qualities in a legal context

No Comments

No Known Activations