INDEX

Explanations

references to revisions in historical and sociopolitical contexts, particularly relating to Marxism and Leninism

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

ending in "ism", "ist", "ists"

np_acts-logits-general · gemini-2.0-flash

doctrines and their adherents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

photobucket

-0.54

 שוליים

-0.53

Diweddarwch

-0.50

pyx

-0.49

Bronnen

-0.48

ウター

-0.48

İstinadlar

-0.47

 AssemblyCompany

-0.47

@"/

-0.47

Initializable

-0.46

POSITIVE LOGITS

ism

1.85

ist

1.69

istic

1.56

ists

1.48

ISM

1.32

isme

1.23

ismo

1.21

ismus

1.19

IST

1.17

ista

1.15

Activations Density 0.222%

references to revisions in historical and sociopolitical contexts, particularly relating to Marxism and Leninism

ending in "ism", "ist", "ists"

doctrines and their adherents

No Comments

No Known Activations