INDEX

Explanations

references to technical components and specifications within systems

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

Mathematical/programming notations and names

np_acts-logits-general · gemini-2.0-flash

each or every

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

makeConstraints

-0.61

 Administrativna

-0.54

 createState

-0.48

AutoScale

-0.47

 ujednoznacz

-0.47

sidemargin

-0.46

SuccessListener

-0.45

setColumns

-0.44

OptionsMenu

-0.43

POSITIVE LOGITS

 each

1.09

 every

0.99

 chaque

0.94

 setiap

0.87

each

0.85

 bawat

0.85

 каждом

0.82

every

0.82

 ognuno

0.82

 каждой

0.80

Activations Density 0.651%

references to technical components and specifications within systems

Mathematical/programming notations and names

each or every

No Comments

No Known Activations

references to technical components and specifications within systems

Mathematical/programming notations and names

each or every

No Comments

No Known Activations