INDEX

Explanations

elements related to CUDA device management and error handling in programming

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

Command-line arguments/parsing

np_acts-logits-general · gemini-2.0-flash

command line arguments and options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/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.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

\{\\

-0.54

blox

-0.51

AddHtmlAttribute

-0.51

}{@

-0.50

 BoxDecoration

-0.49

getDrawable

-0.48

 cellpadding

-0.47

Nul

-0.47

 ContentValues

-0.47

 Integrals

-0.47

POSITIVE LOGITS

 option

1.03

Option

0.98

 argument

0.96

"--

0.96

 getopt

0.95

arg

0.95

Argument

0.95

 Option

0.95

option

0.94

ArgumentParser

0.94

Activations Density 0.327%

elements related to CUDA device management and error handling in programming

Command-line arguments/parsing

command line arguments and options

No Comments

No Known Activations