INDEX

Explanations

references to verification processes in scientific or experimental 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

featureID

-0.78

 betweenstory

-0.73

contentLoaded

-0.68

 autorytatywna

-0.67

verwijspagina

-0.64

 Biôgrafia

-0.64

 سكانية

-0.62

 للاسماء

-0.62

 تضيفلها

-0.61

StoryboardSegue

-0.61

POSITIVE LOGITS

NUMX

0.67

0.63

İstinadlar

0.59

ricated

0.54

ibatis

0.54

 Matériau

0.50

ibly

0.49

 épis

0.49

IDAY

0.49

γωγ

0.49

Activations Density 0.734%

references to verification processes in scientific or experimental contexts

No Comments

No Known Activations

references to verification processes in scientific or experimental contexts

No Comments

No Known Activations