INDEX

Explanations

patterns or phrases related to specific individuals or historical events

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

Armijo, He, Squid

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

astéroïdes

-0.66

 Normdatei

-0.58

 surla

-0.55

Personendaten

-0.52

Jeografia

-0.52

cyklopedia

-0.51

ніципа

-0.51

LayoutStyle

-0.50

WebServlet

-0.50

bootstrapcdn

-0.50

POSITIVE LOGITS

IntoConstraints

0.51

fromnode

0.48

TextBoxColumn

0.35

⅘

0.33

<?

0.33

PreferredItem

0.31

 thăng

0.31

 Sure

0.29

 Tric

0.29

AddTagHelper

0.28

Activations Density 0.034%

patterns or phrases related to specific individuals or historical events

Armijo, He, Squid

No Comments

No Known Activations