INDEX

Explanations

references to addresses and related contact information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ఔ

-0.48

zegor

-0.47

 adelantado

-0.45

ﷺ

-0.45

attva

-0.43

 مرئيه

-0.42

bundet

-0.42

 voulais

-0.42

品

-0.42

品的

-0.42

POSITIVE LOGITS

 address

1.58

 Address

1.48

 ADDRESS

1.39

Address

1.37

 adress

1.34

address

1.31

 addresses

1.29

 adresse

1.25

 Addresses

1.25

 Adress

1.24

Activations Density 0.224%

references to addresses and related contact information

No Comments

No Known Activations