INDEX

Explanations

numerical data or parameters related to visual elements or coordinates in a computational context

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

tě

-0.52

お楽しみに

-0.52

ProgressHUD

-0.50

gantung

-0.48

erweise

-0.48

setVerticalGroup

-0.47

 downright

-0.47

 titik

-0.46

setopt

-0.45

tep

-0.45

POSITIVE LOGITS

 otomatig

0.69

RotationOrder

0.65

 farfetch

0.59

kuuta

0.57

kloped

0.56

otomy

0.55

Rüyada

0.54

#+#

0.53

**/

0.53

ỡi

0.53

Activations Density 0.003%

numerical data or parameters related to visual elements or coordinates in a computational context

No Comments

No Known Activations