INDEX

Explanations

references to social media

oai_token-act-pair · gemini-2.0-flash

social

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

 CiNii

-0.55

PhysRevLett

-0.51

enste

-0.51

ılıyor

-0.51

 chlorine

-0.49

 tapioca

-0.49

usda

-0.49

utnik

-0.48

 skå

-0.48

ⓧ

-0.48

POSITIVE LOGITS

 media

0.59

 medial

0.52

 social

0.51

 medi

0.50

 createState

0.50

󠁢

0.49

pexpr

0.49

 média

0.49

 médias

0.48

IERC

0.47

Activations Density 0.297%

references to social media

social

No Comments

No Known Activations