INDEX

Explanations

technical terms related to assembly and component visibility in programming

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

 AssemblyCulture

-0.77

LookAnd

-0.57

 AssemblyCompany

-0.54

AsUp

-0.54

+#+#

-0.51

IsPostBack

-0.50

 للاسماء

-0.50

PostExecute

-0.49

AntiForgeryToken

-0.49

RenderAtEndOf

-0.48

POSITIVE LOGITS

 ComVisible

1.23

 typelib

0.57

 prêtres

0.40

TabIndex

0.39

 поро

0.38

Dez

0.38

鸿

0.36

eniendo

0.36

ligheter

0.35

 brilh

0.34

Activations Density 0.010%

technical terms related to assembly and component visibility in programming

No Comments

No Known Activations