INDEX

Explanations

mathematical symbols and notations related to equations or formulas

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

Mathematical notation with variables or indices

np_acts-logits-general · gemini-2.0-flash

k

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

 Italijani

-0.64

verwijspagina

-0.63

 gynhyrchwyd

-0.58

GEBURTSDATUM

-0.57

-0.56

rungsseite

-0.55

İY

-0.54

madu

-0.54

 initComponents

-0.53

 للاسماء

-0.52

POSITIVE LOGITS

2.14

2.05

1.99

1.98

Ｋ

1.23

к

1.17

ک

1.11

ｋ

1.10

К

1.10

К

1.05

Activations Density 0.783%

mathematical symbols and notations related to equations or formulas

Mathematical notation with variables or indices

k

No Comments

No Known Activations