INDEX

Explanations

quantifiable data and statistics related to counts or measurements

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

Numbers followed by nouns

np_acts-logits-general · gemini-2.0-flash

numbers followed by units

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

ArrowToggle

-0.38

 betweenstory

-0.32

Решение

-0.31

 Commande

-0.30

łk

-0.30

Portály

-0.29

ÉT

-0.28

 mengak

-0.28

 Transparen

-0.28

modelBuilder

-0.28

POSITIVE LOGITS

MLLoader

0.65

IntoConstraints

0.58

 CreateTagHelper

0.52

 ujednoznacz

0.52

ChildScrollView

0.52

 müſſen

0.52

errHandler

0.52

 câte

0.51

AnimationsModule

0.51

 MainAxisSize

0.50

Activations Density 0.635%

quantifiable data and statistics related to counts or measurements

Numbers followed by nouns

numbers followed by units

No Comments

No Known Activations