INDEX

Explanations

mentions of "property" and related terms within a legal or business context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

-0.77

Према

-0.76

 colorés

-0.74

 dénon

-0.74

 déchir

-0.73

 aveug

-0.73

 sincero

-0.71

 mẽ

-0.71

quelles

-0.71

withstanding

-0.70

POSITIVE LOGITS

 property

3.41

 Property

2.99

property

2.89

Property

2.79

 PROPERTY

2.74

 properties

2.63

PROPERTY

2.53

 Properties

2.23

properties

2.17

Properties

2.06

Activations Density 0.046%

mentions of "property" and related terms within a legal or business context

No Comments

No Known Activations