INDEX

Explanations

technical terms and elements related to scientific methods or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

 hivyo

-0.48

 nahilalakip

-0.48

UpInside

-0.47

andaş

-0.46

 Prud

-0.46

 Famili

-0.44

Ahl

-0.44

 Barbier

-0.44

Favorite

-0.44

 Slov

-0.44

POSITIVE LOGITS

 >=",

0.86

+#+#

0.73

MigrationBuilder

0.71

 onOptions

0.67

ExtendWith

0.67

ValueGeneration

0.64

fitrión

0.63

 فريبيس

0.62

GenerationType

0.60

 Roskov

0.60

Activations Density 0.396%

technical terms and elements related to scientific methods or results

No Comments

No Known Activations