INDEX

Explanations

terms related to formatting and compression in documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

RenderAtEndOf

-0.90

WEBPACK

-0.82

ništ

-0.76

 linkovi

-0.74

出版年

-0.73

ValueStyle

-0.73

 للاسماء

-0.70

BufferException

-0.70

GOTREF

-0.67

DeleteBehavior

-0.66

POSITIVE LOGITS

entially

0.73

 indietro

0.63

pon

0.62

 pyramid

0.60

影响

0.55

peer

0.55

hoc

0.54

 Dara

0.54

 prossimo

0.54

 fundador

0.53

Activations Density 0.033%

terms related to formatting and compression in documents

No Comments

No Known Activations