INDEX

Explanations

results and discussions about data omissions or exclusions in research studies

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

absence or exclusion

np_acts-logits-general · gemini-2.0-flash

excluded or omitted

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

épendance

-0.62

はじめに

-0.57

ípio

-0.55

 AssemblyTitle

-0.54

ViewInit

-0.52

 alleles

-0.49

ISupport

-0.48

BoxShadow

-0.47

gdx

-0.47

 combineReducers

-0.46

POSITIVE LOGITS

 excluded

2.03

 omitted

1.84

 omission

1.74

 exclusion

1.73

 exclude

1.62

excluded

1.60

Excluded

1.49

 excludes

1.46

 missing

1.46

 omissions

1.45

Activations Density 0.521%

results and discussions about data omissions or exclusions in research studies

absence or exclusion

excluded or omitted

No Comments

No Known Activations