INDEX

Explanations

mathematical notations and structures, particularly related to categories, homomorphisms, and dimensionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

PathVariable

-0.56

bootstrapcdn

-0.44

MigrationBuilder

-0.43

$_['

-0.42

 Wikimedijinoj

-0.41

(&:

-0.41

hos

-0.41

UIAlert

-0.40

 demografica

-0.40

">//

-0.40

POSITIVE LOGITS

 oídos

0.49

 nutrisi

0.47

/**

0.44

SequentialGroup

0.44

Населення

0.42

 exámenes

0.42

 réception

0.41

 Zufall

0.41

berdayakan

0.41

horabuena

0.41

Activations Density 2.141%

mathematical notations and structures, particularly related to categories, homomorphisms, and dimensionality

No Comments

No Known Activations