INDEX

Explanations

proper nouns, particularly names and locations

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

place names and organizations

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

PostInfinity

-0.42

 betrekking

-0.41

 influence

-0.40

astéroïdes

-0.39

 pinulongan

-0.38

licone

-0.38

 tell

-0.37

 BytesLike

-0.37

let

-0.37

 terecht

-0.36

POSITIVE LOGITS

CloseOperation

0.67

WebServlet

0.65

setupUi

0.50

RegressionTest

0.49

 Paglinawan

0.48

+#+

0.47

XmlRootElement

0.45

afterEach

0.45

spesies

0.45

IBOutlet

0.45

Activations Density 0.018%

proper nouns, particularly names and locations

place names and organizations

No Comments

No Known Activations