INDEX

Explanations

snippets of informal conversation within documentation and programming Q&A, particularly the word "you" and apostrophes

oai_token-act-pair · gemini-2.0-flash

you

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

abetes

-0.48

</b>

-0.44

SequentialGroup

-0.42

 tố

-0.41

</i>

-0.40

Integra

-0.40

 Integra

-0.40

Gatt

-0.40

}).

-0.40

kon

-0.39

POSITIVE LOGITS

Efq

0.84

NameInMap

0.69

 Theſe

0.65

iffance

0.63

elemField

0.63

 purpoſe

0.60

 zufolge

0.59

 pleaſure

0.59

polation

0.57

 AssemblyCompany

0.57

Activations Density 0.135%

snippets of informal conversation within documentation and programming Q&A, particularly the word "you" and apostrophes

you

No Comments

No Known Activations