INDEX

Explanations

numerical data and statistics

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

phone numbers and their associated formatting characters (parentheses, dashes, and digits).

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 nahilalakip

-0.87

\{\\

-0.74

exitRule

-0.67

évaluateur

-0.67

 beginnetje

-0.65

 ſeyn

-0.65

 zwiſchen

-0.65

 Dieſe

-0.64

<unused8>

-0.64

<unused16>

-0.64

POSITIVE LOGITS

0.29

0.28

 Verdad

0.27

0.26

phosph

0.25

+#+#

0.24

FileOutputStream

0.23

def

0.23

IsPostBack

0.23

Activations Density 0.092%

numerical data and statistics

phone numbers and their associated formatting characters (parentheses, dashes, and digits).

No Comments

No Known Activations