INDEX

Explanations

references to academic positions and affiliations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

academic departments and titles

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 estético

-0.42

 acrylique

-0.39

 kleur

-0.39

 bellezza

-0.38

 egens

-0.38

 prevención

-0.38

zow

-0.37

NOWLEDG

-0.37

ıklı

-0.36

 Ayers

-0.36

POSITIVE LOGITS

BeginInit

0.62

 poffible

0.53

цездатний

0.49

 MonoBehaviour

0.49

 fubject

0.48

 poffe

0.47

roek

0.44

[&

0.44

 primate

0.44

 juſ

0.43

Activations Density 0.021%

references to academic positions and affiliations

academic departments and titles

No Comments

No Known Activations