INDEX

Explanations

phrases indicating user experiences and conditions regarding services and products

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

ConstraintMaker

-0.51

stands

-0.50

์ตูน

-0.50

filler

-0.49

ाला

-0.48

RegressionTest

-0.47

 Kilo

-0.47

glBegin

-0.46

 utafitiHapana

-0.46

kilo

-0.46

POSITIVE LOGITS

 Once

0.75

Once

0.69

 sobald

0.68

once

0.65

 once

0.64

EndInit

0.59

 einmal

0.58

 uintptr

0.57

ONCE

0.57

Datuak

0.57

Activations Density 0.052%

phrases indicating user experiences and conditions regarding services and products

No Comments

No Known Activations