INDEX

Explanations

punctuation marks and phrases indicating direct speech or quotes

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

Numbers at the beginning of the line

np_acts-logits-general · gemini-2.0-flash

names from India

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.28.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

XmlAccessType

-0.66

AnimationsModule

-0.52

principalColumn

-0.45

forName

-0.40

zzleHttp

-0.39

onActivityResult

-0.38

Хьажоргаш

-0.38

 defaultstate

-0.38

 GenerationType

-0.38

 estekak

-0.37

POSITIVE LOGITS

 Paglinawan

0.50

 disambiguazione

0.50

rąg

0.40

zbęd

0.40

 Handwerk

0.39

mire

0.38

 personalise

0.38

llywood

0.38

roek

0.37

Activations Density 0.037%

punctuation marks and phrases indicating direct speech or quotes

Numbers at the beginning of the line

names from India

No Comments

No Known Activations