INDEX

Explanations

terms related to accuracy and precision in measurements or processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Discriminator

-0.55

ijer

-0.52

vfs

-0.50

Alb

-0.50

trend

-0.50

characteristic

-0.50

csol

-0.49

appName

-0.49

ʃ

-0.49

гази

-0.48

POSITIVE LOGITS

 precision

2.43

Precision

2.23

 Precision

2.22

precision

2.21

 Precise

2.11

Precise

2.02

precise

2.00

 precise

1.95

 PRECISION

1.92

 accuracy

1.89

Activations Density 0.095%

terms related to accuracy and precision in measurements or processes

No Comments

No Known Activations