INDEX

Explanations

references to events and their organization

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

figures/supplementary materials

np_acts-logits-general · gemini-2.0-flash

Fig. S

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 חיצוניים

-0.58

WithIOException

-0.56

 varandra

-0.55

 ویکی‌پدیا

-0.54

الإنجليزية

-0.53

VERTISEMENT

-0.52

openSession

-0.52

MERCIAL

-0.51

IBLIO

-0.51

XmlAccessType

-0.48

POSITIVE LOGITS

aarrggbb

0.55

 समीक्षाएं

0.53

 Torrance

0.50

олові

0.49

paramref

0.48

 Privacidade

0.47

 OMIT

0.46

$$$

0.46

Biblia

0.46

 calling

0.46

Activations Density 0.081%

references to events and their organization

figures/supplementary materials

Fig. S

No Comments

No Known Activations