INDEX

Explanations

symbols and notations related to mathematical and technical content

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

Czar, Ben, lies, En

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

存于互联网档案馆

-0.69

 Wikimedijinoj

-0.68

 '\\;'

-0.67

NameInMap

-0.63

 estekak

-0.62

ValueStyle

-0.60

 CreateTagHelper

-0.60

 FetchType

-0.60

Chham

-0.59

Datuak

-0.57

POSITIVE LOGITS

 QtWidgets

0.34

ObjectModel

0.32

 BrowserModule

0.31

дру

0.30

 Mission

0.30

 ramai

0.30

 Guides

0.29

 Railways

0.29

 misiones

0.29

zinho

0.29

Activations Density 0.028%

symbols and notations related to mathematical and technical content

Czar, Ben, lies, En

No Comments

No Known Activations