INDEX

Explanations

references to contributions and acknowledgments in a research context

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

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

 defStyleAttr

-0.51

nmgp

-0.48

 onView

-0.47

AddWithValue

-0.47

refour

-0.47

 समीक्षाओं

-0.46

שְׁ

-0.46

étricas

-0.45

 Gegenteil

-0.45

vedra

-0.44

POSITIVE LOGITS

 donated

2.05

 kindly

1.79

 generously

1.73

 donation

1.71

 donate

1.67

 graciously

1.66

 generosity

1.65

 donating

1.60

 donations

1.51

 generous

1.49

Activations Density 0.356%

references to contributions and acknowledgments in a research context

No Comments

No Known Activations