INDEX

Explanations

references to significant political events or actions

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

dates and events

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

complexType

-0.48

PMailer

-0.45

 ChromeDriver

-0.40

LElement

-0.39

存于互联网档案馆

-0.38

Notae

-0.38

Rujuakan

-0.38

ISupport

-0.38

simpleType

-0.37

ตอบ

-0.36

POSITIVE LOGITS

AppMethodBeat

0.56

 للمعارف

0.50

localctx

0.44

PreferredItem

0.41

 surla

0.40

ことができました

0.39

 autorytatywna

0.37

CopyWith

0.37

 gymnas

0.37

WaitGroup

0.36

Activations Density 0.116%

references to significant political events or actions

dates and events

No Comments

No Known Activations