INDEX

Explanations

documentation and comments in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 TestBed

-0.46

libft

-0.44

Παραπομπές

-0.41

 uLocal

-0.41

UrlEncoded

-0.40

 Administrativna

-0.39

FOS

-0.39

 calib

-0.39

 ✭✭

-0.39

 fore

-0.38

POSITIVE LOGITS

MessageTagHelper

0.67

retudo

0.52

 miniaturka

0.50

 capuz

0.46

WriteTagHelper

0.45

dientemente

0.43

ósitos

0.42

 BoxDecoration

0.42

LabelTagHelper

0.41

 Represents

0.41

Activations Density 0.075%

documentation and comments in programming code

No Comments

No Known Activations

documentation and comments in programming code

No Comments

No Known Activations