INDEX

Explanations

technical terms and concepts related to computer architecture and memory management

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ⓧ

-0.59

 tartalomajánló

-0.44

 Infórmanos

-0.42

antd

-0.42

 للاسماء

-0.41

EnableWeb

-0.41

脚注の使い方

-0.41

 NgModule

-0.39

Microkernel

-0.37

떻

-0.37

POSITIVE LOGITS

uintptr

0.56

 uintptr

0.48

 Addresses

0.45

erçe

0.43

pośred

0.43

addresses

0.43

納

0.42

]")]

0.42

//-----

0.42

PrototypeOf

0.41

Activations Density 1.127%

technical terms and concepts related to computer architecture and memory management

No Comments

No Known Activations