INDEX

Explanations

data structures and references within code or technical documents

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

References, citations, or links

np_acts-logits-general · gemini-2.0-flash

bracketed references and data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 AssemblyVersion

-0.39

 Italijani

-0.36

AddHtmlAttribute

-0.33

 ExecuteAsync

-0.32

 quoi

-0.32

 salva

-0.32

Jîn

-0.32

typ

-0.32

astéroïdes

-0.31

Diwedd

-0.30

POSITIVE LOGITS

 valentín

0.54

 scattata

0.53

 imprensa

0.52

dafx

0.51

ModelAdmin

0.51

 ſein

0.50

 ModelExpression

0.50

 صوتيه

0.50

原始内容存档

0.49

 laſſen

0.49

Activations Density 1.817%

data structures and references within code or technical documents

References, citations, or links

bracketed references and data

No Comments

No Known Activations