INDEX

Explanations

technical terms and components related to programming and software development

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

module imports and assignments

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ftagPool

-0.81

ReusableCell

-0.78

PerformLayout

-0.76

webElementXpaths

-0.76

setVerticalGroup

-0.75

awtextra

-0.73

invokeLater

-0.72

EndContext

-0.72

Vidite

-0.72

 للمعارف

-0.69

POSITIVE LOGITS

 nôtre

0.36

 vôtre

0.35

node

0.30

 muere

0.30

pustakaan

0.29

ínico

0.28

 encargada

0.28

škas

0.28

 infraestructura

0.28

riften

0.28

Activations Density 0.005%

technical terms and components related to programming and software development

module imports and assignments

No Comments

No Known Activations