INDEX

Explanations

technical terminology and approximations related to physical phenomena and their modeling

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

Approximation or approximates

np_acts-logits-general · gemini-2.0-flash

approximations and closest values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.30.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

posedge

-0.54

 Infórmanos

-0.50

Jereo

-0.48

IsMutable

-0.48

webElementXpaths

-0.42

OrNil

-0.42

WithIOException

-0.42

تقاوى

-0.40

RefNanny

-0.40

 GenerationType

-0.38

POSITIVE LOGITS

 approximation

1.95

 approximations

1.74

 approximate

1.73

 approximates

1.68

 approximated

1.65

 Approximation

1.61

 approximating

1.52

 approxim

1.48

approximate

1.45

 Approximate

1.43

Activations Density 1.536%

technical terminology and approximations related to physical phenomena and their modeling

Approximation or approximates

approximations and closest values

No Comments

No Known Activations