INDEX

Explanations

numerical values related to visual properties and layout in web design or programming

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

code snippets in different languages

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 ब्रेकडाउन

-0.48

 متعلقه

-0.46

ViewImports

-0.44

 상세

-0.43

Lycka

-0.39

 MainAxisSize

-0.39

ecz

-0.37

 mistrzost

-0.36

ñado

-0.36

minecraftforge

-0.35

POSITIVE LOGITS

setVerticalGroup

0.67

CreateModel

0.52

rawDesc

0.50

parsedMessage

0.50

ChildScrollView

0.50

Vidite

0.49

CppMethod

0.48

GEBURTSDATUM

0.48

stateMutability

0.47

Дереккөздер

0.46

Activations Density 0.015%

numerical values related to visual properties and layout in web design or programming

code snippets in different languages

No Comments

No Known Activations