INDEX

Explanations

references to "mass" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

theless

-0.78

 rhubarb

-0.76

präche

-0.76

 Vivaldi

-0.71

 Ronde

-0.70

 anticoag

-0.70

crip

-0.69

 Viter

-0.68

 converti

-0.68

 виправивши

-0.67

POSITIVE LOGITS

 mass

2.80

 Mass

2.75

Mass

2.56

mass

2.52

MASS

2.28

 MASS

2.26

 masses

2.02

 Massen

1.92

 Masses

1.90

masses

1.77

Activations Density 0.067%

references to "mass" in various contexts

No Comments

No Known Activations