INDEX

Explanations

terms related to machine learning model evaluation and feature selection techniques

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

SourceChecksum

-0.71

ChildScrollView

-0.70

AndEndTag

-0.69

 jScrollPane

-0.68

脚注の使い方

-0.64

Autoritní

-0.63

曖昧さ回避

-0.63

Efq

-0.61

ElementException

-0.60

AllAfrica

-0.59

POSITIVE LOGITS

 learning

0.56

 training

0.54

 sklearn

0.54

keras

0.51

lern

0.49

tensorflow

0.48

 keras

0.47

Regressor

0.47

svm

0.45

 epoca

0.44

Activations Density 0.573%

terms related to machine learning model evaluation and feature selection techniques

No Comments

No Known Activations