INDEX

Explanations

mathematical concepts and notations related to limits, probabilities, and optimization 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 يتيمه

-0.59

पया

-0.54

TagMode

-0.54

 мәкал

-0.48

 Roskov

-0.47

PYX

-0.46

parsedMessage

-0.45

kozások

-0.44

amssymb

-0.43

 gärna

-0.43

POSITIVE LOGITS

erializer

0.38

 greatest

0.38

 dragons

0.37

 Dragons

0.37

RetentionPolicy

0.36

sendRedirect

0.35

koc

0.35

 Involved

0.35

igrafi

0.34

 fuel

0.34

Activations Density 2.584%

mathematical concepts and notations related to limits, probabilities, and optimization in proofs

No Comments

No Known Activations