INDEX

Explanations

elements of computer code, particularly those involving file paths, names, and operations

oai_token-act-pair · gemini-2.0-flash

code references and structures

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

parenthesis and quotes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.69

-0.68

份

-0.52

int

-0.49

eng

-0.48

ct

-0.47

-0.46

ex

-0.45

get

-0.45

ter

-0.44

POSITIVE LOGITS

 ModelExpression

1.05

 estekak

0.88

 '\\;'

0.83

bootstrapcdn

0.81

 Lightboxes

0.81

oredCriteria

0.81

parsedMessage

0.81

ItemBackground

0.80

 CURIAM

0.79

 Мексичка

0.79

Activations Density 0.718%

elements of computer code, particularly those involving file paths, names, and operations

code references and structures

parenthesis and quotes

No Comments

No Known Activations