INDEX

Explanations

references to geographical locations and institutions in British Columbia

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 proposons

-0.48

 genannt

-0.48

 voire

-0.46

asInstanceOf

-0.46

mick

-0.45

ate

-0.45

ATE

-0.44

 dispositif

-0.43

acyjna

-0.43

ignements

-0.43

POSITIVE LOGITS

 Toronto

1.36

 Canadians

1.36

 Canada

1.34

 Canadian

1.32

 CANADA

1.30

 Calgary

1.28

 CANADIAN

1.27

 RCMP

1.26

Toronto

1.26

 Ontario

1.25

Activations Density 0.883%

references to geographical locations and institutions in British Columbia

No Comments

No Known Activations