INDEX

Explanations

technical terms and their contextual usage in programming and algorithm discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

bootstrapcdn

-0.48

仮想

-0.43

LETIN

-0.39

RegressionTest

-0.39

 الرياضيه

-0.39

 khai

-0.38

 ujednoznacz

-0.38

attrs

-0.38

นอก

-0.37

 antigens

-0.37

POSITIVE LOGITS

 noDo

0.59

adpleegd

0.46

DIPSETTING

0.46

 continúas

0.43

hyrchwyd

0.43

jgl

0.42

 OMITBAD

0.42

 famí

0.41

fromnode

0.41

Spoljašnje

0.41

Activations Density 1.275%

technical terms and their contextual usage in programming and algorithm discussions

No Comments

No Known Activations