INDEX

Explanations

terms related to quantum mechanics, specifically those regarding entanglement and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

rófono

-0.48

 miss

-0.45

EditorBrowsable

-0.43

 Marchand

-0.43

ole

-0.42

 Lightfoot

-0.42

 Chromat

-0.41

 Chré

-0.41

стар

-0.41

rhosis

-0.41

POSITIVE LOGITS

 quantum

1.08

 Quantum

0.95

Quantum

0.89

quantum

0.88

量子

0.86

 qubit

0.80

 entanglement

0.68

 eaves

0.62

 entangled

0.60

__["

0.59

Activations Density 1.479%

terms related to quantum mechanics, specifically those regarding entanglement and measurements

No Comments

No Known Activations