INDEX

Explanations

keywords and mentions of editorial roles or positions

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

出版年

-0.53

httphttps

-0.52

 Gemeinden

-0.48

 BoxFit

-0.48

pii

-0.47

 excu

-0.45

 attempted

-0.41

pirazione

-0.40

NgModule

-0.40

 dramatique

-0.40

POSITIVE LOGITS

tinyos

0.66

AnchorTagHelper

0.62

mobileqq

0.60

hyrchwyd

0.60

Autoritní

0.60

 Biôgrafia

0.59

Founded

0.58

ValueStyle

0.58

AutoModerator

0.56

 thyself

0.56

Activations Density 0.187%

keywords and mentions of editorial roles or positions

No Comments

No Known Activations