INDEX

Explanations

mathematical symbols and notations in equations

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

Mathematical equation labels

np_acts-logits-general · gemini-2.0-flash

latex labels

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

()

-0.40

()

-0.39

BASEPATH

-0.38

 SafeMath

-0.37

 barriga

-0.34

landet

-0.33

(;

-0.33

itsa

-0.33

 lätt

-0.33

pezif

-0.33

POSITIVE LOGITS

出版年

1.05

+#+#

1.00

 Paglinawan

0.96

 referenties

0.93

 للمعارف

0.90

 Wicidata

0.89

IntoConstraints

0.89

GEBURTSDATUM

0.87

 defaultstate

0.87

TagMode

0.86

Activations Density 0.089%

mathematical symbols and notations in equations

Mathematical equation labels

latex labels

No Comments

No Known Activations