INDEX

Explanations

mathematical notation especially those with subscripts and superscripts

oai_token-act-pair · gemini-2.0-flash

{

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Numerade

-0.63

<bos>

-0.60

 disambiguazione

-0.57

WriteLiteral

-0.56

下载附件

-0.54

Autoritní

-0.54

disposing

-0.53

rizona

-0.50

reportWebVitals

-0.50

 Normdatei

-0.49

POSITIVE LOGITS

 snippetHide

0.71

CppMethod

0.57

obium

0.55

 المعيارى

0.54

GMENT

0.54

 lievito

0.53

 Вікі

0.53

 Chwiliwch

0.53

achuca

0.52

Isk

0.51

Activations Density 2.129%

mathematical notation especially those with subscripts and superscripts

{

No Comments

No Known Activations