INDEX

Explanations

references to filtering methods and their efficiency

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

 wobec

-0.39

PasswordEncoder

-0.35

atchewan

-0.33

 bijzonder

-0.32

 fréquent

-0.32

 marchandises

-0.31

 kalangan

-0.31

specialchars

-0.31

 ویکی‌پدی

-0.30

 Angaben

-0.29

POSITIVE LOGITS

 filming

0.98

 filters

0.95

Plot

0.95

Fil

0.94

 Plot

0.91

 filmed

0.91

 filtr

0.91

Fil

0.90

 Filters

0.88

plot

0.85

Activations Density 0.301%

references to filtering methods and their efficiency

No Comments

No Known Activations