INDEX

Explanations

symbols and mathematical notations used in complex equations and proofs

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

mathematical notation variables and symbols

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

WebServlet

-0.68

 estekak

-0.66

Portale

-0.59

+#+#

-0.56

بوابة

-0.56

 viewWillAppear

-0.54

ViewFeatures

-0.54

usercontent

-0.54

 мәкал

-0.54

 surla

-0.53

POSITIVE LOGITS

šno

0.34

事

0.34

食い

0.32

 infierno

0.32

 لان

0.32

imbang

0.32

 moldes

0.32

ėmis

0.31

jména

0.31

hingga

0.31

Activations Density 0.277%

symbols and mathematical notations used in complex equations and proofs

mathematical notation variables and symbols

No Comments

No Known Activations