INDEX

Explanations

references to artificial neural networks and their applications in various fields

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

 propOrder

-0.60

 Chwiliwch

-0.57

Personendaten

-0.53

 AssemblyVersion

-0.48

ftagPool

-0.47

tagHelperRunner

-0.47

出版年

-0.46

bcryptjs

-0.46

OGND

-0.45

tinyos

-0.45

POSITIVE LOGITS

ViewImports

0.64

 MainAxisSize

0.51

 pinulongan

0.50

setViewportView

0.45

professional

0.45

 kasarigan

0.44

itative

0.43

 professional

0.43

 disponibilités

0.43

Dono

0.42

Activations Density 1.317%

references to artificial neural networks and their applications in various fields

No Comments

No Known Activations