INDEX

Explanations

code snippets, especially those with numbers in the syntax.

oai_token-act-pair · gemini-2.0-flash

numbers

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

 ModelExpression

-0.94

 EconPapers

-0.92

 चीज़ों

-0.88

 jScrollPane

-0.81

Попис

-0.77

styleType

-0.75

 كومونز

-0.75

 OFDb

-0.73

ⓧ

-0.73

HtmlAttribute

-0.71

POSITIVE LOGITS

0.54

0.50

0.49

0.48

事

0.45

0.41

hpp

0.40

0.39

pro

0.38

Activations Density 21.663%

code snippets, especially those with numbers in the syntax.

numbers

No Comments

No Known Activations