INDEX

Explanations

specific nouns and terms associated with publishing and media

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

Datuak

-0.59

 décrire

-0.56

теристика

-0.53

RegressionTest

-0.52

djangoproject

-0.51

Captor

-0.50

पया

-0.49

 descri

-0.49

 safely

-0.46

matchCondition

-0.45

POSITIVE LOGITS

DoubleQuotes

0.71

StoryboardSegue

0.61

 manuscript

0.60

expandindo

0.58

TRON

0.56

 المعيارى

0.56

 manuscripts

0.56

ymce

0.56

 Audience

0.55

Audience

0.54

Activations Density 0.932%

specific nouns and terms associated with publishing and media

No Known Activations