INDEX

Explanations

code snippets related to programming and technical queries

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code-related questions and answers

np_acts-logits-general · gemini-2.0-flash

asking questions or stating problems

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Incidentally

-0.53

 setUsername

-0.49

 hendak

-0.48

 intptr

-0.47

inSlope

-0.47

 Whilst

-0.46

Whilst

-0.46

 whilst

-0.46

 poichè

-0.45

 Amongst

-0.44

POSITIVE LOGITS

 technics

0.57

 employes

0.57

 informations

0.57

 للاسماء

0.52

 Beside

0.52

 realy

0.50

 fuckin

0.49

 east

0.49

 lenght

0.48

Exemple

0.48

Activations Density 0.963%

code snippets related to programming and technical queries

Code-related questions and answers

asking questions or stating problems

No Comments

No Known Activations