INDEX

Explanations

references to food and food-related items

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

 verle

-0.88

marginHorizontal

-0.87

trise

-0.86

__]

-0.86

']],

-0.85

%]

-0.84

 amethyst

-0.83

 Plume

-0.83

 AssemblyCompany

-0.83

azy

-0.81

POSITIVE LOGITS

 food

2.03

 Food

1.88

food

1.76

 FOOD

1.72

Food

1.70

FOOD

1.65

 foods

1.47

 Foods

1.33

foods

1.24

Foods

1.15

Activations Density 0.030%

references to food and food-related items

No Comments

No Known Activations