INDEX

Explanations

terms, code, syntax and variables related to computer programming

oai_token-act-pair · gemini-2.0-flash

words with special characters and alternate spellings

np_token-act-pair-logits · gpt-4o-mini

say period replacements

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 piłkarz

-0.57

TOMS

-0.49

');?>

-0.49

/*!

-0.49

 miglior

-0.48

 او

-0.47

sar

-0.46

equalTo

-0.46

acas

-0.46

 plata

-0.45

POSITIVE LOGITS

 Theſe

0.84

ſelves

0.66

 Beſ

0.65

Tikang

0.63

 Anſ

0.61

afficheront

0.60

 myſelf

0.60

 itſelf

0.60

MMdd

0.60

 Jefus

0.60

Activations Density 5.595%

terms, code, syntax and variables related to computer programming

words with special characters and alternate spellings

say period replacements

No Comments

No Known Activations