INDEX

Explanations

phrases that indicate substitution or customization of products

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

product operability

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

CppMethod

-0.52

RenderAtEndOf

-0.44

GOTREF

-0.44

 autorytatywna

-0.42

Portale

-0.41

دانشنامهٔ

-0.41

CloseOperation

-0.40

AnchorStyles

-0.40

nesium

-0.39

tzmann

-0.37

POSITIVE LOGITS

 Torneo

0.42

 linkovi

0.40

harusnya

0.39

፩

0.39

게

0.38

awtextra

0.37

 faune

0.37

newcommand

0.36

 sobě

0.36

gameserver

0.36

Activations Density 0.011%

phrases that indicate substitution or customization of products

product operability

No Comments

No Known Activations