INDEX

Explanations

specific food items and ingredients in a recipe context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

 quæ

-0.71

 habet

-0.67

SequentialGroup

-0.60

 mobili

-0.57

 Poincar

-0.56

 suor

-0.55

 Schmuck

-0.55

 Poincaré

-0.55

 quidem

-0.53

 ratified

-0.53

POSITIVE LOGITS

 garnish

0.89

 seasoning

0.87

 ingredients

0.87

 sauce

0.85

 topping

0.83

 cooked

0.82

 INGREDIENTS

0.82

 sauté

0.82

 ingredient

0.81

 sauces

0.81

Activations Density 0.295%

specific food items and ingredients in a recipe context

No Comments

No Known Activations