INDEX

Explanations

technical terms and parameters related to scientific data and measurements

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

 یہ

-0.46

payee

-0.45

 particularly

-0.41

тури

-0.41

Pro

-0.41

 Especially

-0.41

 плат

-0.40

 http

-0.40

ortunadamente

-0.40

 Just

-0.40

POSITIVE LOGITS

 itſelf

0.81

mybatisplus

0.70

phazard

0.70

viewDidLoad

0.66

 viewDidLoad

0.62

 purpoſe

0.62

 CascadeType

0.62

MatButtonModule

0.62

 Reſ

0.61

 himſelf

0.61

Activations Density 1.203%

technical terms and parameters related to scientific data and measurements

No Comments

No Known Activations