INDEX

Explanations

elements of programming syntax and mathematical expressions

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

"mod" or "modulo" operations

np_acts-logits-general · gemini-2.0-flash

modulo operation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 EconPapers

-0.77

 للمعارف

-0.77

 الحره

-0.76

tvguidetime

-0.75

 disambiguazione

-0.75

PhysRevD

-0.74

 فريبيس

-0.74

 nahilalakip

-0.72

contentLoaded

-0.72

 صوتيه

-0.70

POSITIVE LOGITS

mod

1.56

mod

1.43

Mod

1.37

Mod

1.32

 modulo

1.24

MOD

1.21

bmod

1.19

MOD

1.18

 modulus

1.10

modulo

1.03

Activations Density 0.555%

elements of programming syntax and mathematical expressions

"mod" or "modulo" operations

modulo operation

No Comments

No Known Activations