INDEX

Explanations

concepts related to evidence and its implications

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

EOUT

-0.55

 Roskov

-0.52

Chú

-0.47

 Paglinawan

-0.47

ge

-0.47

 cuantos

-0.47

 high

-0.46

high

-0.46

 deep

-0.46

繰り

-0.45

POSITIVE LOGITS

aarrggbb

0.82



0.80

MessageOf

0.70

ModelAdmin

0.68

 nutella

0.66

出版年

0.64

ApiOperation

0.63

nonatomic

0.63

WithFormat

0.63

okovic

0.63

Activations Density 0.099%

concepts related to evidence and its implications

No Known Activations