INDEX

Explanations

specific XML tags and their attributes, particularly those involving "read," "write," "data," "delim," and "match".

oai_token-act-pair · gemini-2.0-flash

angle brackets and characters within XML-like tags

np_token-act-pair-logits · gemini-2.0-flash

Non-English or code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_16/width_16k/average_l0_10

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

UnusedPrivate

-0.49

 СПб

-0.44

entech

-0.44

-0.43

erun

-0.43

vikle

-0.43

[][]

-0.43

زاد

-0.42

 років

-0.42

variates

-0.42

POSITIVE LOGITS

 للاسماء

0.75

 متعلقه

0.75

 Italijanski

0.70

存于互联网档案馆

0.68

]")]

0.65

tvguidetime

0.65

UnitTesting

0.62

 snippetHide

0.61

 estekak

0.60

AnchorStyles

0.60

Activations Density 7.093%

specific XML tags and their attributes, particularly those involving "read," "write," "data," "delim," and "match".

angle brackets and characters within XML-like tags

Non-English or code

No Comments

No Known Activations