INDEX

Explanations

a diverse set of technical words related to finance, genetics, religion, computer programming, and legalese

oai_token-act-pair · gemini-2.0-flash

finance

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

出版年

-0.55

migrations

-0.53

 Netto

-0.52

 LUMP

-0.51

 cảnh

-0.50

.$,

-0.48

 Forces

-0.46

CACHE

-0.45

humanité

-0.45

 nationaux

-0.45

POSITIVE LOGITS

addCriterion

0.76

<?

0.68

<bos>

0.65

astéroïdes

0.63

HasBeenSet

0.63

 '\\;'

0.62

tinyos

0.60

 noDo

0.59

 snippetHide

0.58

extAlignment

0.57

Activations Density 0.608%

a diverse set of technical words related to finance, genetics, religion, computer programming, and legalese

finance

No Comments

No Known Activations