INDEX

Explanations

numerical data and values related to scientific experiments

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

numbers and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 nahilalakip

-0.84



-0.70

Билгалдахарш

-0.61

adaptiveStyles

-0.59

 مشين

-0.59

 EconPapers

-0.54

ScopeManager

-0.52

ViewFeatures

-0.50

 للاسماء

-0.49

ArgumentParser

-0.49

POSITIVE LOGITS

IntoConstraints

0.57

Personendaten

0.50

 invitamos

0.43

sizeCache

0.38

Egypte

0.38

vician

0.36

horabuena

0.36

JvmStatic

0.36

гъ

0.35

usammen

0.34

Activations Density 0.152%

numerical data and values related to scientific experiments

numbers and measurements

No Comments

No Known Activations