INDEX

Explanations

HTML tags and elements within a document

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

disambiguation page links

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

mybatisplus

-0.49

Hozzáférés

-0.45

 الاطلاع

-0.42

orre

-0.41

GENERATED

-0.41

 setEmail

-0.40

abstractmethod

-0.38

 canst

-0.38

saraba

-0.38

 utafitiHapana

-0.38

POSITIVE LOGITS

 ujednoznacz

0.70

 disambiguazione

0.62

ViewFeatures

0.61

tagHelperRunner

0.56

rungsseite

0.54

 autorytatywna

0.53

verwijspagina

0.52

Personensuche

0.51

 ProtoMessage

0.49

期刊论文

0.49

Activations Density 0.001%

HTML tags and elements within a document

disambiguation page links

No Comments

No Known Activations