INDEX

Explanations

phrases related to data handling and processing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

TypedDataSet

-0.67

 algunos

-0.61

 algunas

-0.59

 algumas

-0.57

 estimés

-0.56

 alguns

-0.55

 some

-0.50

 quelques

-0.50

jini

-0.48

bouncycastle

-0.48

POSITIVE LOGITS

 Everything

0.94

everything

0.93

Everything

0.92

Tudo

0.90

Semua

0.90

 everything

0.88

 imaginable

0.86

 đều

0.83

Alles

0.82

 EVERYTHING

0.81

Activations Density 0.517%

phrases related to data handling and processing

No Comments

No Known Activations