INDEX

Explanations

phrases indicating a sequence or result

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

ScopeManager

-0.74

cycline

-0.62

RegressionTest

-0.61

 weren

-0.59

atriz

-0.59

ollectionView

-0.57

IntoConstraints

-0.57

__":

-0.56

columbia

-0.56

TestingModule

-0.56

POSITIVE LOGITS

adaptiveStyles

0.76

IsContent

0.62

Попис

0.62

othea

0.57

BBBB

0.57

ividual

0.56

rijfs

0.54

ódios

0.54

 himſelf

0.54

sizeCache

0.54

Activations Density 0.006%

phrases indicating a sequence or result

No Comments

No Known Activations