INDEX

Explanations

mathematical symbols and terms related to variables and functions

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

Mathematical/scientific notation and formulas

np_acts-logits-general · gemini-2.0-flash

prime notation

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

OGND

-0.70

 ब्रेकडाउन

-0.68

 ویکی‌پدی

-0.66

تقاوى

-0.66

AccessorTable

-0.63

 queſta

-0.60

Vidite

-0.60

цездатний

-0.59

 cherchés

-0.59

ंदीखरीदारी

-0.59

POSITIVE LOGITS

 Olsson

0.58

 Baumann

0.53

 escultura

0.52

 península

0.52

 Jorg

0.51

 capucha

0.49

 emosi

0.49

 Cardoso

0.49

 Cronin

0.49

 caixa

0.49

Activations Density 11.773%

mathematical symbols and terms related to variables and functions

Mathematical/scientific notation and formulas

prime notation

No Comments

No Known Activations