INDEX

Explanations

technical terms related to data processing and programming

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

 propOrder

-0.69

 ویکی‌پدیا

-0.63

unnitel

-0.56

 AssemblyVersion

-0.54

featureID

-0.52

 Option

-0.49

")==

-0.49

parseDouble

-0.49

NamedQueries

-0.49

 mapStateToProps

-0.48

POSITIVE LOGITS

uxxxx

0.81

addCriterion

0.59

حوالہ

0.57

cotch

0.52

 extremes

0.50

+/-

0.49

windowFixed

0.49

InOut

0.48

+-

0.48

quias

0.48

Activations Density 1.667%

technical terms related to data processing and programming

No Comments

No Known Activations