INDEX

Explanations

specific types of meats and dishes often featured in culinary discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

RegressionTest

-0.95

 AssemblyCulture

-0.90

 فريبيس

-0.90

rrggbb

-0.84

principalTable

-0.76

 ویکی‌پدیای

-0.76

Portail

-0.72

Vidite

-0.72

 للمعارف

-0.70

PHA

-0.70

POSITIVE LOGITS

 meat

1.32

meat

1.10

 beef

1.02

 MEAT

1.00

 meats

0.99

 Meat

0.98

 steak

0.95

Meat

0.95

 pork

0.93

fleisch

0.93

Activations Density 0.120%

specific types of meats and dishes often featured in culinary discussions

No Comments

No Known Activations