INDEX

Explanations

terms and concepts related to particle physics and the Standard Model

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.80

 שוליים

-0.79

出版年

-0.74

ngdoc

-0.72

HttpFoundation

-0.69

DockStyle

-0.68

حياته

-0.68

 AssemblyProduct

-0.67

granate

-0.66

Coordonnées

-0.65

POSITIVE LOGITS

 Standard

0.53

 neutrino

0.52

Standard

0.51

 neutrinos

0.50

 gange

0.45

PhysRevD

0.45

 Weih

0.44

сла

0.43

 maso

0.43

CP

0.41

Activations Density 0.772%

terms and concepts related to particle physics and the Standard Model

No Comments

No Known Activations