INDEX

Explanations

references to artificial elements and their applications or effects

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

 BUSH

-0.42

เปล

-0.41

yog

-0.41

FileVersion

-0.38

Loose

-0.38

 facult

-0.37

dæ

-0.37

맷

-0.36

 slut

-0.36

 уме

-0.36

POSITIVE LOGITS

 artificially

0.90

 artificial

0.82

 künst

0.78

artificial

0.70

人工

0.67

 unnatural

0.63

synthetic

0.62

 artificiales

0.61

 Artificial

0.60

Artificial

0.57

Activations Density 0.938%

references to artificial elements and their applications or effects

No Comments

No Known Activations