INDEX

Explanations

words and phrases related to news and reporting, especially direct quotes and source attributions

oai_token-act-pair · gemini-2.0-flash

News agencies

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

 éto

-0.58

createServer

-0.51

وصلات

-0.50

 насељу

-0.47

openConnection

-0.46

yatı

-0.46

 muualla

-0.45

\{\\

-0.45

didSet

-0.44

 população

-0.43

POSITIVE LOGITS

 Reuters

0.69

AFP

0.68

AFP

0.67

 agency

0.63

Reuters

0.60

ристання

0.59

 agencies

0.59

UTERS

0.57

Agence

0.56

 news

0.55

Activations Density 0.746%

words and phrases related to news and reporting, especially direct quotes and source attributions

News agencies

No Comments

No Known Activations