INDEX

Explanations

terms related to data modeling and analysis in the context of high-dimensional datasets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

LEncoder

-0.77

PerformLayout

-0.67

astify

-0.65

XmlType

-0.64

onAttach

-0.62

 initComponents

-0.62

ScopeManager

-0.57

tagext

-0.57

VersionUID

-0.56

ftagPool

-0.56

POSITIVE LOGITS

 data

2.20

data

1.74

 dataset

1.54

 Data

1.53

数据

1.51

 datasets

1.50

 Daten

1.47

 DATA

1.44

Data

1.43

データ

1.39

Activations Density 1.549%

terms related to data modeling and analysis in the context of high-dimensional datasets

No Comments

No Known Activations