INDEX

Explanations

terms related to programming and documentation, particularly focusing on functionality and parameters

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

derive or determine

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

queryInterface

-0.41

lwjgl

-0.39

eddings

-0.37

endaft

-0.37

ymus

-0.37

 dataSnapshot

-0.36

dafx

-0.36

पन

-0.35

anko

-0.34

POSITIVE LOGITS

 Италијани

0.61

 ویکی‌پدی

0.54

hoeddwyd

0.50

setVerticalGroup

0.50

IVEREF

0.50

expandindo

0.49

 للاسماء

0.48

دانشنامهٔ

0.48

лтамалар

0.47

Diwedd

0.47

Activations Density 0.137%

terms related to programming and documentation, particularly focusing on functionality and parameters

derive or determine

No Comments

No Known Activations