INDEX

Explanations

phrases related to statistical modeling and measurements involving latent processes

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

Data simulations and high-dimensional data

np_acts-logits-general · gemini-2.0-flash

data acquisition and analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

PerformLayout

-1.01

LEncoder

-0.76

astify

-0.72

Obrázky

-0.67

 ***!

-0.66

WriteBarrier

-0.66

 autorytatywna

-0.65

StructEnd

-0.64

UnusedPrivate

-0.63

#+#

-0.62

POSITIVE LOGITS

 data

1.92

data

1.48

 observations

1.42

数据

1.33

 Data

1.28

 DATA

1.25

 dataset

1.23

データ

1.22

 datasets

1.22

Data

1.21

Activations Density 1.839%

phrases related to statistical modeling and measurements involving latent processes

Data simulations and high-dimensional data

data acquisition and analysis

No Comments

No Known Activations