INDEX

Explanations

mentions of the term "Powell" and variations of it

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

Powell, math pow

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

/*

-0.52

/*

-0.50

 Angelina

-0.49

setupUi

-0.49

Indian

-0.49

Italian

-0.48

Martin

-0.47

Ita

-0.46

expandindo

-0.46

 Regina

-0.45

POSITIVE LOGITS

Pow

1.17

 Powell

1.07

Powell

1.02

Pow

1.02

pow

0.99

pow

0.95

POW

0.86

POW

0.81

 Power

0.75

 powders

0.68

Activations Density 0.005%

mentions of the term "Powell" and variations of it

Powell, math pow

No Comments

No Known Activations