INDEX

Explanations

references to Australia and its various locations and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

ModelSerializer

-0.65

illig

-0.63

 spacy

-0.58

 initComponents

-0.57

Kna

-0.57

 ghiaccio

-0.56

DataField

-0.56

DispatchToProps

-0.56

 Burnham

-0.54

 Achille

-0.54

POSITIVE LOGITS

 Australian

2.58

Australian

2.36

 Sydney

2.31

 Australia

2.29

 Aussie

2.29

 Australians

2.19

Sydney

2.14

 Melbourne

2.13

Australia

2.07

 australian

2.06

Activations Density 0.067%

references to Australia and its various locations and entities

No Comments

No Known Activations