INDEX

Explanations

references to blog posts and updates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

EndContext

-0.41

">//

-0.39

 propOrder

-0.35

wußt

-0.33

 <<<<<<<<<<<<<<

-0.32

 stället

-0.31

 daß

-0.30

 personales

-0.30

μβρίου

-0.29

 domésticos

-0.28

POSITIVE LOGITS

 onboarding

0.60

хьтан

0.59

 webinars

0.55

ThroughAttribute

0.54

Jereo

0.53

SceneManagement

0.52

 Blockly

0.50

 engagement

0.50

 spotlight

0.49

 anniversaries

0.49

Activations Density 0.477%

references to blog posts and updates

No Comments

No Known Activations