INDEX

Explanations

database-related terms and structure definitions

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

aarrggbb

-0.63

 EconPapers

-0.54

 tartalomajánló

-0.54

 disambiguazione

-0.49

...

-0.48

Dowell

-0.48

 '\\;'

-0.48

 famí

-0.48

tvguidetime

-0.47

RTEX

-0.46

POSITIVE LOGITS

AxisAlignment

0.66

AddHtmlAttribute

0.61

onAttach

0.59

 villaggio

0.57

ácidos

0.57

idać

0.57

endant

0.56

Formik

0.56

 panoramique

0.56

audiovisuel

0.54

Activations Density 0.026%

database-related terms and structure definitions

No Known Activations