INDEX

Explanations

mathematical terms and concepts related to conditions and restrictions in proofs

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

worth

-0.44

WORTH

-0.43

(&:

-0.43

 WORTH

-0.40

AMENTO

-0.40

imp

-0.39

 worth

-0.39

alamus

-0.39

liam

-0.39

DateTimeField

-0.38

POSITIVE LOGITS

 ligiloj

0.59

 endforeach

0.57

 betweenstory

0.57

addCriterion

0.53

endforeach

0.49

 חיצוניים

0.49

 Comprometido

0.48

 ब्रेकडाउन

0.47

 Infórmanos

0.46

 pprint

0.46

Activations Density 0.616%

mathematical terms and concepts related to conditions and restrictions in proofs

No Comments

No Known Activations