INDEX

Explanations

phrases that indicate the presence of specific medical conditions or studies

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

esModule

-0.63

awaiter

-0.59

 consultato

-0.58

ể

-0.58

 geslacht

-0.56

 SEDS

-0.52

 विश्वसनीयता

-0.50

tifies

-0.50

||=

-0.50

AddHtmlAttribute

-0.49

POSITIVE LOGITS

ThroughAttribute

0.68

PreferredItem

0.60

 урна

0.56

mäs

0.56

 dépla

0.54

eadilan

0.53

Xna

0.52

ArrowToggle

0.52

UnitTesting

0.52

 استنادى

0.50

Activations Density 0.029%

phrases that indicate the presence of specific medical conditions or studies

No Comments

No Known Activations