INDEX

Explanations

references to continuous variables or continuous functions in the context of statistical models

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

Negative Logits

 spéciaux

-0.76

SuppressLint

-0.73

 éché

-0.68

 pomme

-0.67

 šal

-0.67

kul

-0.66

setViewName

-0.65

 sauvages

-0.64

 Pompeii

-0.64

 Macca

-0.63

POSITIVE LOGITS

Continuous

1.38

 continuous

1.34

 CONTIN

1.34

 Continuous

1.32

continuous

1.31

CONTIN

1.29

 contin

1.27

 Continu

1.24

Contin

1.23

 Contin

1.23

Activations Density 0.037%

references to continuous variables or continuous functions in the context of statistical models

No Known Activations