INDEX

Explanations

terms related to classification and data analysis methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 démocr

-0.56

 varandra

-0.53

 acaso

-0.52

abilirsiniz

-0.51

ViewFeatures

-0.50

conhe

-0.50

 militaires

-0.49

 chré

-0.46

 habet

-0.46

 quæ

-0.46

POSITIVE LOGITS

XmlAccessType

0.82

BufferException

0.77

Hauptartikel

0.75

 /\.(

0.74

 AssemblyTitle

0.72

GEBURTS

0.71

Архівовано

0.71

ValueGeneration

0.70

ervlak

0.70

 >=",

0.70

Activations Density 0.496%

terms related to classification and data analysis methodologies

No Comments

No Known Activations