INDEX

Explanations

occurrences of the term "Car" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.40.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

numerusform

-0.41

 razon

-0.39

 civil

-0.39

كويكب

-0.38

InputTagHelper

-0.37

Atsauces

-0.37

 avoient

-0.36

bufio

-0.36

 étoient

-0.36

Kor

-0.35

POSITIVE LOGITS

AddTagHelper

0.58

AndEndTag

0.58

 Мексичка

0.54

richTextPanel

0.46

 ویکی‌پدی

0.45

IsContent

0.43

 comuniques

0.42

 ***!

0.42

SourceChecksum

0.41

ftagPool

0.41

Activations Density 0.218%

occurrences of the term "Car" in various contexts

No Comments

No Known Activations