INDEX

Explanations

programming constructs and symbols related to code structure and function definitions

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

JTabbedPane

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

WriteLiteral

-0.48

uxxxx

-0.47

Искәрмәләр

-0.47

 pinulongan

-0.45

Lähteet

-0.44

 pungkasnya

-0.43

 EconPapers

-0.43

oğlu

-0.42

didSet

-0.42

enumii

-0.41

POSITIVE LOGITS

 surla

0.45

 intptr

0.44

UrlResolution

0.41

 barbati

0.38

 للاسماء

0.38

Organisateur

0.37

 betweenstory

0.37

 Wilhel

0.36

 continúas

0.36

EDEFAULT

0.36

Activations Density 0.087%

programming constructs and symbols related to code structure and function definitions

JTabbedPane

No Comments

No Known Activations