INDEX

Explanations

references to presentations and related concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

ParallelGroup

-0.72

oneofs

-0.70

catchError

-0.62

 MonoBehaviour

-0.61

σιμοποι

-0.60

Portály

-0.59

bledon

-0.58

antaine

-0.57

fjspx

-0.57

invokeLater

-0.56

POSITIVE LOGITS

 presentation

2.39

Presentation

2.29

 Presentation

2.21

 presentations

2.14

presentation

2.12

 PRESENTATION

1.97

 Presentations

1.81

Presentations

1.66

 Präsentation

1.43

 présentation

1.41

Activations Density 0.093%

references to presentations and related concepts

No Comments

No Known Activations