INDEX

Explanations

Code snippets

np_max-act-logits · gemini-2.0-flash

parts of code defining classes and methods, especially in C++

oai_token-act-pair · gemini-2.0-flash

code-like words

np_token-act-pair-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

+#+#

-0.58

 '\\;'

-0.54

 متعلقه

-0.51

脚注の使い方

-0.51

 étrangères

-0.50

 consultato

-0.49

ineno

-0.49

viewWillAppear

-0.48

ViewFeatures

-0.48

uxxxx

-0.48

POSITIVE LOGITS

 AssemblyProduct

0.56

άνι

0.54

ciuto

0.52

 installed

0.49

&[

0.48

}>{

0.47

 bubbles

0.47

 butterknife

0.47

 polypropylene

0.47

ğinde

0.47

Activations Density 2.056%

Code snippets

parts of code defining classes and methods, especially in C++

code-like words

No Comments

No Known Activations