INDEX

Explanations

C++ code snippets related to arrays and median calculations

oai_token-act-pair · gemini-2.0-flash

code and array manipulation

np_token-act-pair-logits · gemini-2.0-flash

code snippets

np_max-act-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

ViewFeatures

-0.69

 NDEBUG

-0.69

/**

-0.68

لينكات

-0.67

Personendaten

-0.64

 ↓,

-0.60

richTextPanel

-0.60

BeginContext

-0.60

GEBURTSDATUM

-0.60

featureID

-0.59

POSITIVE LOGITS

теп

0.47

 UIApplication

0.45

 fontsize

0.44

par

0.41

ategories

0.41

Par

0.41

لسط

0.41

ampiyon

0.40

 stands

0.40

ANTLR

0.40

Activations Density 3.711%

C++ code snippets related to arrays and median calculations

code and array manipulation

code snippets

No Comments

No Known Activations