INDEX

Explanations

statistical terms and references to robust estimation methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 Rudd

-0.73

 Anja

-0.72

Bris

-0.70

 تانيه

-0.69

XmlRootElement

-0.69

 télé

-0.68

 Meth

-0.68

 StringTokenizer

-0.67

mrs

-0.66

stagland

-0.65

POSITIVE LOGITS

parsedMessage

0.99

 necesite

0.80

tara

0.79

 Dyke

0.79

 Psyche

0.78

Ache

0.78

 виправивши

0.78

 AssemblyCompany

0.76

醐

0.75

 Tara

0.74

Activations Density 3.239%

statistical terms and references to robust estimation methods

No Comments

No Known Activations