INDEX

Explanations

technical terms and concepts related to programming and data processing

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

discussing options or solutions

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

 disambiguazione

-0.45

#+#

-0.45

GIVEREF

-0.40

 vuotta

-0.39

Erfolge

-0.39

 hittar

-0.37

libft

-0.36

ご注意

-0.35

 Erscheinung

-0.34

лтемелер

-0.34

POSITIVE LOGITS

UserScript

0.67

 للاسماء

0.50

/***/

0.46

GraphicsUnit

0.45

 Rela

0.44

WithIOException

0.44

scryfall

0.43

Diwedd

0.43

interopRequire

0.42

 cận

0.41

Activations Density 0.273%

technical terms and concepts related to programming and data processing

discussing options or solutions

No Comments

No Known Activations