INDEX

Explanations

mathematical notation related to quantum mechanics and integrals

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

ThroughAttribute

-0.69

 Roskov

-0.68

Xun

-0.65

 sorella

-0.65

 vader

-0.63

bukkit

-0.63

Билгалдахарш

-0.63

 Numerade

-0.62

 soeur

-0.62

POSITIVE LOGITS

langle

1.90

〈

1.18

rangle

1.16

⟨

1.00

〈

0.94

〈

0.93

csname

0.86

lceil

0.79

"><?=

0.77

〉

0.76

Activations Density 0.077%

mathematical notation related to quantum mechanics and integrals

No Comments

No Known Activations