INDEX

Explanations

language related to allegations and claims of wrongdoing

oai_token-act-pair · gemini-2.0-flash

Accusations

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ніципалі

-0.58

 RSSSF

-0.52

 tarko

-0.50

تفصیلات

-0.50

UIControlState

-0.49

Datuak

-0.49

SequentialGroup

-0.48

niksi

-0.48

inheritDoc

-0.48

 tribute

-0.48

POSITIVE LOGITS

 allegations

1.37

 allegation

1.30

 accusations

1.27

 accusation

1.26

 claims

1.19

accus

1.12

 charges

1.09

Alleg

1.07

 claim

1.04

 accuse

1.01

Activations Density 2.208%

language related to allegations and claims of wrongdoing

Accusations

No Comments

No Known Activations