INDEX

Explanations

proper nouns and names in citations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 quite

-0.53

endforeach

-0.51

遁

-0.49

toli

-0.48

 closely

-0.48

zole

-0.48

vur

-0.46

 endforeach

-0.46

 like

-0.46

olski

-0.45

POSITIVE LOGITS

ftagPool

0.85

 فريبيس

0.80

UnifiedTopology

0.77

 lenker

0.77

PreferredItem

0.73

 Italijanski

0.72

providedIn

0.72

 समीक्षक

0.71

цездатний

0.70

 Italijani

0.69

Activations Density 0.257%

proper nouns and names in citations

No Comments

No Known Activations