INDEX

Explanations

terms related to magnetic interactions and properties in materials science

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

 alimentaires

-0.41

 quelcon

-0.40

bewerken

-0.38

 sûrement

-0.38

 étoit

-0.38

 ainfi

-0.37

 plufieurs

-0.36

 étoient

-0.36

PMailer

-0.36

 saluran

-0.35

POSITIVE LOGITS

 spin

0.81

 spins

0.80

 Spin

0.76

 magnetization

0.71

Spin

0.69

spin

0.67

 ddelweddau

0.65

 exchange

0.62

 ferro

0.60

 SPIN

0.60

Activations Density 1.030%

terms related to magnetic interactions and properties in materials science

No Comments

No Known Activations