INDEX

Explanations

references to hierarchical structures and their components

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

/**

-0.31

 contemporáneo

-0.29

//

-0.28

 Mazz

-0.28

 must

-0.28

-0.27

ne

-0.27

gus

-0.27

้อน

-0.27

 Neuf

-0.26

POSITIVE LOGITS

child

1.32

Child

1.05

CHILD

1.01

 Child

0.98

childs

0.97

ReusableCell

0.94

 getChild

0.94

 autorytatywna

0.94

 child

0.92

 CHILD

0.91

Activations Density 0.056%

references to hierarchical structures and their components

No Comments

No Known Activations