INDEX

Explanations

technical terms and conditions related to assessments and evaluations

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

"mod" and related mathematical terms

np_acts-logits-general · gemini-2.0-flash

modulo operation, remainder

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

PhysRevD

-0.79

 فريبيس

-0.76

 EconPapers

-0.76

 للمعارف

-0.74

 nahilalakip

-0.68

tvguidetime

-0.68

ScopeManager

-0.67

 Seeder

-0.65

TagHelper

-0.64

 ujednoznacz

-0.61

POSITIVE LOGITS

mod

1.63

mod

1.51

Mod

1.39

Mod

1.36

 modulo

1.34

bmod

1.26

MOD

1.24

 modulus

1.22

MOD

1.20

modulo

1.06

Activations Density 0.781%

technical terms and conditions related to assessments and evaluations

"mod" and related mathematical terms

modulo operation, remainder

No Comments

No Known Activations