INDEX

Explanations

technical terms and classifications related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.33.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

OGND

-0.72

 للاسماء

-0.69

 <<<<<<<<<<<<<<

-0.66

 otomatig

-0.63

awtextra

-0.62

 فريبيس

-0.61

 nakalista

-0.60

 ***!

-0.60

 ویکی‌پدی

-0.59

abestanden

-0.57

POSITIVE LOGITS

CloseOperation

0.58

 Bourgoin

0.45

 verden

0.44

Sdn

0.43

hilangan

0.43

 NgModule

0.42

antası

0.41

esgue

0.41

 sendiri

0.40

 Roumanie

0.40

Activations Density 4.952%

technical terms and classifications related to programming and software development

No Comments

No Known Activations