INDEX

Explanations

technical terms related to programming and object-oriented design

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

kháu

-0.56

exitRule

-0.56

TypedDataSet

-0.51

HandlerContext

-0.48

 kaarangay

-0.48

AndEndTag

-0.47

 Chwiliwch

-0.47

Демографія

-0.46

writeFieldEnd

-0.45

 verdict

-0.45

POSITIVE LOGITS

FromNib

0.41

 Umum

0.39

 décédé

0.38

 太郎

0.36

 estekak

0.36

 mourut

0.35

 ioutil

0.35

 StatelessWidget

0.35

 LIRE

0.35

 insuffisamment

0.35

Activations Density 0.499%

technical terms related to programming and object-oriented design

No Comments

No Known Activations