INDEX

Explanations

sequences of numerical data or IDs associated with patents and research studies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/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.0.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

 desmotivaciones

-1.56

 ainfi

-1.41

 increí

-1.32

 queſta

-1.32

 plufieurs

-1.31

 avoient

-1.29

 ویکی‌پدی

-1.27

 feroit

-1.27

parsedMessage

-1.23

pecabe

-1.23

POSITIVE LOGITS

1.51

1.34

↵

1.32

1.29

1.25

1.22

1.18

1.17

1.16

Activations Density 1.491%

sequences of numerical data or IDs associated with patents and research studies

No Comments

No Known Activations