INDEX

Explanations

research-related terminology and concepts pertaining to cognitive tasks and attention

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

InjectMocks

-0.71

mbggenerated

-0.61

DebuggerNonUser

-0.59

abstractmethod

-0.54

Kanpo

-0.53

parsedMessage

-0.52

ChildScrollView

-0.52

ROIT

-0.50

武将

-0.50

paramref

-0.50

POSITIVE LOGITS

 EconPapers

0.70

Pum

0.65

 psychologists

0.65

 Baños

0.60

 meringue

0.57

ngths

0.57

 psychologie

0.56

 Dissolved

0.55

 Broke

0.55

 Armin

0.55

Activations Density 0.237%

research-related terminology and concepts pertaining to cognitive tasks and attention

No Known Activations