INDEX

Explanations

location identifiers and addresses

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

 propOrder

-0.83

aarrggbb

-0.71

 ujednoznacz

-0.69

ロウィン

-0.69

 EconPapers

-0.64



-0.63

Ӕ

-0.62



-0.61



-0.59

ViewInit

-0.58

POSITIVE LOGITS

Sar

0.33

 train

0.33

Sar

0.29

щь

0.28

 يتيمه

0.28

 court

0.27

end

0.27

Alt

0.26

 hurt

0.26

Activations Density 0.454%

location identifiers and addresses

No Comments

No Known Activations