INDEX

Explanations

code snippets, especially those in languages like C or C++

oai_token-act-pair · gemini-2.0-flash

programming language syntax elements and keywords

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

code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WebVitals

-0.78

contentLoaded

-0.69

Ծանոթ

-0.69

Referencies

-0.68

SequentialGroup

-0.65

Rujuakan

-0.63

 plagioclase

-0.63

 समीक्षक

-0.63

typeorm

-0.63

brada

-0.63

POSITIVE LOGITS

no

0.56

Lo

0.53

lo

0.49

DoubleQuotes

0.46

sk

0.45

ох

0.45

lore

0.45

tr

0.45

Sk

0.43

mense

0.42

Activations Density 0.296%

code snippets, especially those in languages like C or C++

programming language syntax elements and keywords

code

No Comments

No Known Activations