INDEX

Explanations

repeated patterns or structures in data

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

patients and women

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

 indígen

-0.51

 óptica

-0.50

 Kebijakan

-0.47

 directiva

-0.46

 serpiente

-0.44

 căr

-0.43

 préstamos

-0.43

 burbuja

-0.43

cartão

-0.43

POSITIVE LOGITS

 nahilalakip

0.63

 Numerade

0.59

 autorytatywna

0.56

tagHelperRunner

0.56

 Roskov

0.53

 незавершена

0.53

Попис

0.53

Diweddarwch

0.52

XmlAccessType

0.47

хьтан

0.47

Activations Density 0.001%

repeated patterns or structures in data

patients and women

No Comments

No Known Activations

repeated patterns or structures in data

patients and women

No Comments

No Known Activations