INDEX

Explanations

terms related to descriptions and characterizations in legal or analytical contexts

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

writeHead

-0.65

inot

-0.57

 topics

-0.56

 Topics

-0.56

 Topic

-0.56

 sommeil

-0.55

ség

-0.55

Ingredienti

-0.55

 buttons

-0.54

 Cereal

-0.54

POSITIVE LOGITS

reactstrap

0.76

 HasFactory

0.68

AntiForgeryToken

0.67

RLock

0.62

 davon

0.56

ardless

0.56

jenner

0.56

Portail

0.56

теризу

0.55

 ourselves

0.54

Activations Density 0.114%

terms related to descriptions and characterizations in legal or analytical contexts

No Comments

No Known Activations