INDEX

Explanations

statistical terms and metrics used in data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 jaka

-0.45

 someone

-0.40

 referring

-0.40

 Referring

-0.38

+/**

-0.37

Someone

-0.36

脚注の使い方

-0.36

queles

-0.36

 sollen

-0.35

someone

-0.35

POSITIVE LOGITS

 autorytatywna

0.69

AutoField

0.55

Personendaten

0.52

BASEPATH

0.51

IsContent

0.48

HtmlAttribute

0.48

httphttps

0.47

➟

0.47

ollectionView

0.45

 jsPsych

0.44

Activations Density 0.257%

statistical terms and metrics used in data analysis

No Comments

No Known Activations