INDEX

Explanations

technical terms and references related to mathematical distributions and test statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jalá

-0.44

RectangleBorder

-0.41

InputBorder

-0.40

 PeEnEo

-0.39

-0.34

ChildScrollView

-0.33

AutoScaleMode

-0.33

ArgsConstructor

-0.31

 Generales

-0.30

avenir

-0.30

POSITIVE LOGITS

تقاوى

0.60

SourceChecksum

0.56

 للاسماء

0.54

 Normdatei

0.53

Jeografia

0.53

 Walkover

0.51

styleable

0.49

XtraGrid

0.47

 esternos

0.47

 protoimpl

0.45

Activations Density 0.188%

technical terms and references related to mathematical distributions and test statistics

No Comments

No Known Activations