INDEX

Explanations

specific types of terms or definitions related to scientific or technical topics

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

uminense

-0.55

}{*}{}

-0.51

 eventdata

-0.48

ViewFeatures

-0.46

Javadoc

-0.46

 Preferencias

-0.44

setupUi

-0.44

 Daddy

-0.43

arote

-0.42

Naissance

-0.42

POSITIVE LOGITS

ContentAsync

0.66

 quæ

0.62

 habet

0.61

TypedDataSet

0.58

 doInBackground

0.58

Datuak

0.58

TestingModule

0.58

neté

0.57

 blanches

0.56

ñora

0.55

Activations Density 0.118%

specific types of terms or definitions related to scientific or technical topics

No Comments

No Known Activations