INDEX

Explanations

terms and concepts related to programming, specifically in web development and software engineering

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

user conversations

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

IsMutable

-0.49

 betweenstory

-0.48

Vidite

-0.47

 vectorielles

-0.45

 CanadaChoose

-0.45

richTextPanel

-0.45

 "..\..\..\

-0.44

Tikang

-0.44

 useAppContext

-0.44

Démographie

-0.43

POSITIVE LOGITS

minecraft

0.91

 utafitiHapana

0.45

참고

0.45

 lung

0.42

inc

0.40

antino

0.38

 arri

0.38

 tanah

0.37

ctest

0.37

 AssemblyCompany

0.36

Activations Density 0.001%

terms and concepts related to programming, specifically in web development and software engineering

user conversations

No Comments

No Known Activations