INDEX

Explanations

phrases indicating initial steps or points of departure for a discussion or process

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

SequentialGroup

-0.71

PreExecute

-0.69

reactstrap

-0.68

 lenker

-0.62

GEBURTSDATUM

-0.60

MockBean

-0.60

localctx

-0.59

invokeLater

-0.59

Etimología

-0.58

webElementXpaths

-0.57

POSITIVE LOGITS

starter

0.60

MessageInfo

0.59

 starter

0.57

 nakalista

0.56

yelidikan

0.55

Starter

0.55

 Starter

0.53

arrón

0.53

 gyhoeddwyd

0.52

 étape

0.50

Activations Density 0.022%

phrases indicating initial steps or points of departure for a discussion or process

No Comments

No Known Activations

phrases indicating initial steps or points of departure for a discussion or process

No Comments

No Known Activations