INDEX

Explanations

mathematical expressions and notations

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

MigrationBuilder

-0.43

 laiton

-0.42

NotBlank

-0.40

settle

-0.39

Rüyada

-0.39

Données

-0.38

 Bailly

-0.38

SuspendLayout

-0.38

🛈

-0.37

 Wikiseite

-0.37

POSITIVE LOGITS

Xna

0.59

twimg

0.51

 blin

0.48

 Oregon

0.48

#+#

0.48

libft

0.48

 Portland

0.47

oregon

0.45

CPtr

0.45

Portland

0.45

Activations Density 0.205%

mathematical expressions and notations

No Comments

No Known Activations