INDEX

Explanations

numbers and mathematical expressions

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

numerical equations and variables

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

makeConstraints

-0.66

msgTypes

-0.65

 disambiguazione

-0.65

oredCriteria

-0.60

KommentareTeilen

-0.60

ſſung

-0.59

⩕

-0.59

𐑥

-0.59

 pageNumber

-0.59

idlertid

-0.58

POSITIVE LOGITS

 ویکی‌پدی

0.30

<>("

0.28

Paths

0.26

HasAnnotation

0.26

 EClass

0.25

 فريبيس

0.25

sor

0.25

kesan

0.24

paths

0.23

╗

0.23

Activations Density 0.233%

numbers and mathematical expressions

numerical equations and variables

No Comments

No Known Activations