INDEX

Explanations

words and phrases that indicate opinions, reviews, or evaluations of something.

oai_token-act-pair · gemini-2.0-flash

blowing

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

addContainerGap

-0.49

CrossRef

-0.48

 évit

-0.48

🩹

-0.47

 useRouter

-0.46

pch

-0.46

colorbar

-0.46

狞

-0.45

 prenn

-0.45

tidaknya

-0.45

POSITIVE LOGITS

wow

1.05

 blown

0.99

 blew

0.98

 blow

0.94

 blowing

0.87

wow

0.87

WOW

0.84

blowing

0.84

da

0.84

 enchant

0.83

Activations Density 1.859%

words and phrases that indicate opinions, reviews, or evaluations of something.

blowing

No Comments

No Known Activations