INDEX

Explanations

names of reporters and publications with associated keywords like "by", "times", "reporter"

oai_token-act-pair · gemini-2.0-flash

journalist

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

AddHtmlAttribute

-0.74

 esternos

-0.63

adpleegd

-0.63

 لينك

-0.62

 الحره

-0.60

ⓧ

-0.60

AsUp

-0.59

 Audiodateien

-0.58

ModelSerializer

-0.58

GEBURTSDATUM

-0.55

POSITIVE LOGITS

はじめに

0.56

inja

0.49

 otim

0.48

BeginContext

0.48

allin

0.44

 wartawan

0.43

mistic

0.42

 wirk

0.41

Activations Density 0.864%

names of reporters and publications with associated keywords like "by", "times", "reporter"

journalist

No Comments

No Known Activations