INDEX

Explanations

references to kitchen-related terms and items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

новниш

-0.95

phosa

-0.93

RSpec

-0.90

Cordialement

-0.88



-0.88

ValueStyle

-0.87

apunov

-0.86

 Noto

-0.85

Efq

-0.85

 themſelves

-0.84

POSITIVE LOGITS

 kitchen

1.50

 Kitchen

1.37

Kitchen

1.31

 kitchens

1.28

kitchen

1.28

 KITCHEN

1.14

ITCHEN

1.12

 kitchenette

0.88

 Kitchens

0.83

 Kitch

0.81

Activations Density 0.040%

references to kitchen-related terms and items

No Comments

No Known Activations