INDEX

Explanations

snippets of code, specifically related to setting parameters and returning values in API requests, along with some date abbreviations from other languages.

oai_token-act-pair · gemini-2.0-flash

Code punctuation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 myſelf

-1.53

Efq

-1.39

 Monfieur

-1.36

 purpoſe

-1.33

 Jefus

-1.31

 againſt

-1.30

 becauſe

-1.30

 themſelves

-1.30

 himſelf

-1.30

 whoſe

-1.29

POSITIVE LOGITS

0.84

0.71

0.68

0.66

0.65

</

0.65

<eos>

0.65

Activations Density 3.023%

snippets of code, specifically related to setting parameters and returning values in API requests, along with some date abbreviations from other languages.

Code punctuation

No Comments

No Known Activations