INDEX

Explanations

references to premium quality or premium products

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

Slf

-0.67

lossians

-0.66

etCode

-0.61

 Ives

-0.58

Messi

-0.58

MENAFN

-0.57

 ActionListener

-0.57

 Boca

-0.56

preduce

-0.56

vtk

-0.56

POSITIVE LOGITS

 premium

3.40

premium

3.16

 Premium

3.13

Premium

3.02

 PREMIUM

2.75

 premiums

2.68

PREMI

2.22

 Premi

2.12

プレミアム

1.83

premi

1.75

Activations Density 0.047%

references to premium quality or premium products

No Comments

No Known Activations