INDEX

Explanations

elements related to technical specifications and definitions within a programming or computational context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 secundario

-0.44

berdayakan

-0.42

OrBuilder

-0.41

reszcie

-0.40

 cuáles

-0.40

 kepad

-0.39

Begriffsklä

-0.39

 faltan

-0.39

IsMutable

-0.38

 sekal

-0.38

POSITIVE LOGITS

 Majefty

0.77

 Cæsar

0.72

transQ

0.66

 Hiram

0.65

 Samara

0.63

 bauer

0.63

Mila

0.62

 Medusa

0.62

 Houſe

0.61

 nonatomic

0.60

Activations Density 0.259%

elements related to technical specifications and definitions within a programming or computational context

No Comments

No Known Activations