INDEX

Explanations

references to mathematical formulas and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 defaultstate

-1.38

RectangleBorder

-1.36

Efq

-1.31

 nahilalakip

-1.28

 myſelf

-1.23

 disambiguazione

-1.23

 Houſe

-1.21

adaptiveStyles

-1.21

 Monfieur

-1.19

 itſelf

-1.19

POSITIVE LOGITS

 formula

0.90

inger

0.70

0.69

expr

0.68

formula

0.66

 Formula

0.64

 fórmula

0.63

0.62

公式

0.61

0.60

Activations Density 0.100%

references to mathematical formulas and equations

No Comments

No Known Activations