INDEX

Explanations

technical terms related to interference and interaction effects in data analysis

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

"inter", "intere", "interfere", "interact", or "interpolate"

np_acts-logits-general · gemini-2.0-flash

interference, intervention, interaction, intersection

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

 Pugh

-0.78

AndEndTag

-0.66

 Aleg

-0.65

 Blaze

-0.65

 propOrder

-0.62

 Searle

-0.61

 Mahoney

-0.58

 Shoemaker

-0.58

Kig

-0.57

Blaze

-0.56

POSITIVE LOGITS

 INTER

2.34

inter

2.24

 Inter

2.19

INTER

2.18

Inter

2.16

 inter

2.15

 interference

1.63

 interface

1.55

 intere

1.52

 Интер

1.52

Activations Density 0.343%

technical terms related to interference and interaction effects in data analysis

"inter", "intere", "interfere", "interact", or "interpolate"

interference, intervention, interaction, intersection

No Comments

No Known Activations