INDEX

Explanations

terms related to statistical significance and representation in research contexts

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

-0.63

crata

-0.57

SOUNDBITE

-0.56

principalColumn

-0.54

DataBind

-0.52

ISODE

-0.52

InjectMocks

-0.52

tableFuture

-0.50

RestController

-0.50

 surla

-0.50

POSITIVE LOGITS

Proportion

0.58

 répartition

0.57

proportion

0.53

 proportion

0.53

Propor

0.52

 distribuzione

0.50

 distribution

0.50

 proportions

0.49

 reprodução

0.49

 Proportion

0.49

Activations Density 0.514%

terms related to statistical significance and representation in research contexts

No Comments

No Known Activations