INDEX

Explanations

mentions of authors in texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

RuleContext

-0.67

 vanskelig

-0.52

Añ

-0.51

 vooraf

-0.48

dlc

-0.48

APT

-0.47

 riuscito

-0.47

ῖν

-0.47

 uſed

-0.46

 falso

-0.46

POSITIVE LOGITS

author

2.34

 author

1.66

 Author

1.58

Author

1.56

AUTHOR

1.49

 AUTHOR

1.47

Authors

1.10

authors

1.08

autor

1.04

 AssemblyCompany

1.04

Activations Density 0.035%

mentions of authors in texts

No Comments

No Known Activations