INDEX

Explanations

geographic locations, particularly states and cities in the United States and Japan

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

geographical locations

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

Билгалдахарш

-0.63

 ویکی‌پدی

-0.63



-0.61

цездатний

-0.59

AISSEE

-0.54

UserScript

-0.53

Panamoan

-0.53

 nahilalakip

-0.53

DIPSETTING

-0.52

Спасылкі

-0.52

POSITIVE LOGITS

enregistrement

0.39

 diensten

0.39

談社

0.38

 termica

0.38

üyor

0.35

 Schall

0.35

acamata

0.34

atteindre

0.34

 thuận

0.34

akuan

0.33

Activations Density 0.016%

geographic locations, particularly states and cities in the United States and Japan

geographical locations

No Comments

No Known Activations