INDEX

Explanations

occurrences of the word "prototype" and its variations in a programming 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

 paſſ

-0.58

 Inquis

-0.55

Qar

-0.55

Kör

-0.54

Wiz

-0.54

Eſ

-0.53

 ſtate

-0.52

 tranſ

-0.51

herr

-0.51

 Kwan

-0.51

POSITIVE LOGITS

prototype

4.36

 prototype

2.52

Prototype

2.37

 Prototype

2.37

 prototypes

2.21

原型

1.74

 PROTO

1.55

PROTO

1.50

 Proto

1.50

 prototyping

1.45

Activations Density 0.049%

occurrences of the word "prototype" and its variations in a programming context

No Comments

No Known Activations