INDEX

Explanations

references to laws and legal principles

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

power-law scaling and exponents

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 OnInit

-0.56

cestershire

-0.53

expandindo

-0.52

MigrationBuilder

-0.52

Obrázky

-0.51

sweise

-0.51

 surla

-0.50

charest

-0.48

 Administrativna

-0.48

ynchronous

-0.48

POSITIVE LOGITS

law

2.31

LAW

1.75

laws

1.41

Law

1.32

lav

1.16

LAW

1.10

law

1.07

ław

1.04

Law

1.03

Laws

0.90

Activations Density 0.005%

references to laws and legal principles

power-law scaling and exponents

No Comments

No Known Activations