INDEX

Explanations

mathematical expressions and symbols used in equations

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

Mathematical or statistical notation

np_acts-logits-general · gemini-2.0-flash

function components (x , w, z, t , b)

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

 Avez

-0.56

 Bere

-0.55

تف

-0.49

 fata

-0.49

 Zell

-0.49

Viited

-0.47

Bere

-0.46

ِّف

-0.45

 Sisters

-0.45

 bate

-0.45

POSITIVE LOGITS

 surla

0.75

sidemargin

0.75

contentLoaded

0.74

 Roskov

0.74

DeleteMapping

0.70

Diweddarwch

0.68

Демографія

0.67

 متعلقه

0.66

expandindo

0.65

 kommunen

0.63

Activations Density 0.702%

mathematical expressions and symbols used in equations

Mathematical or statistical notation

function components (x , w, z, t , b)

No Comments

No Known Activations