INDEX

Explanations

references to figures and the formatting attributes associated with them in documents

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

 purpoſe

-0.51

 ſte

-0.51

Tembelea

-0.48

########.

-0.46

 pleaſure

-0.46

PRNewswire

-0.44

 Jefus

-0.44

ſelves

-0.44

ſelf

-0.44

 arşivlendi

-0.44

POSITIVE LOGITS

 EconPapers

0.57

 AssemblyVersion

0.53

 width

0.50

InputBorder

0.48

 renda

0.45

 onCreateView

0.44

styleUrls

0.44

XmlAccessorType

0.44

 AssemblyProduct

0.43

 GenerationType

0.42

Activations Density 0.091%

references to figures and the formatting attributes associated with them in documents

No Comments

No Known Activations