INDEX

Explanations

terms related to legal concepts and laws

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

expandindo

-0.72

 Италијани

-0.71

 gynhyrchwyd

-0.70

клопе

-0.69

Efq

-0.69

SqlSession

-0.68

 utafitiHapana

-0.67

 Meksiku

-0.66

 صوتيه

-0.66

utilisons

-0.65

POSITIVE LOGITS

ditionally

0.53

Traditional

0.52

 Traditionally

0.49

 traditional

0.47

 Traditional

0.47

 carab

0.47

шир

0.47

npmjs

0.46

medies

0.46

ne

0.45

Activations Density 0.001%

terms related to legal concepts and laws

No Comments

No Known Activations