INDEX

Explanations

phone numbers and addresses, potentially extracting contact information.

oai_token-act-pair · gemini-2.0-flash

Seattle

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gradle

-0.59

 Kombat

-0.53

RegressionTest

-0.52

 vPvB

-0.52

gmd

-0.50

atchewan

-0.50

 Réponses

-0.49

EndInit

-0.48

dena

-0.47

iibo

-0.47

POSITIVE LOGITS

esModule

0.61

 viewDidLoad

0.60

 Isolated

0.56

principalColumn

0.55

eat

0.52

 ControllerBase

0.49

setContentView

0.49

ưỡi

0.48

MigrationBuilder

0.47

 considérons

0.47

Activations Density 0.433%

phone numbers and addresses, potentially extracting contact information.

Seattle

No Comments

No Known Activations