INDEX

Explanations

database-related terms and constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 disambiguazione

-1.18

 autorytatywna

-0.85

Parcelize

-0.85

rungsseite

-0.83

Personensuche

-0.81

SequentialGroup

-0.81

BagConstraints

-0.77

 estekak

-0.76

 chi̍t

-0.75

 سكانية

-0.75

POSITIVE LOGITS

rait

0.42

 hObject

0.41

nalités

0.41

opensource

0.41

UIC

0.41

<u>

0.40

rial

0.40

 vivent

0.39

end

0.39

Activations Density 0.180%

database-related terms and constructs

No Comments

No Known Activations