INDEX

Explanations

code snippets related to graphics processing unit (GPU) performance optimization and function definitions

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

"max" followed by assignment or comparison operators

np_acts-logits-general · gemini-2.0-flash

best or max compute

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

 ſche

-0.59

PerformLayout

-0.59

ArrowToggle

-0.57

parsedMessage

-0.57

DECREF

-0.54

Leif

-0.51

 myſelf

-0.51

franchise

-0.51

endpush

-0.50

 AppColors

-0.50

POSITIVE LOGITS

évaluateur

0.45

 ukuran

0.43

richTextPanel

0.40

 Betrachtung

0.37

 regels

0.36

 wedstrijd

0.36

 accesibles

0.36

 orgullo

0.35

 Autorisations

0.35

 considération

0.34

Activations Density 0.142%

code snippets related to graphics processing unit (GPU) performance optimization and function definitions

"max" followed by assignment or comparison operators

best or max compute

No Comments

No Known Activations