INDEX

Explanations

references to actions and procedures taken

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

 Seventy

-0.47

@@@@@

-0.46

 seventy

-0.45

 Öffentlichkeit

-0.44

 TestBed

-0.44

 Kobayashi

-0.43

 Griswold

-0.43

Throughout

-0.42

 ninety

-0.41

 extranjeros

-0.41

POSITIVE LOGITS

 Action

1.41

 action

1.40

 ACTION

1.38

Action

1.38

action

1.34

getAction

1.27

 Actions

1.20

ACTION

1.15

IAction

1.12

 ACTIONS

1.12

Activations Density 0.152%

references to actions and procedures taken

No Comments

No Known Activations