INDEX

Explanations

references to legal and regulatory entities or frameworks

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

court rules and guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 EconPapers

-0.74

 TextAppearance

-0.56

 ProtoMessage

-0.52

 defaultstate

-0.52

featureID

-0.50

 utafitiHapana

-0.50

المكان

-0.49

 BorderSide

-0.48

aarrggbb

-0.48

 maravillas

-0.47

POSITIVE LOGITS

 guidelines

0.48

 accepted

0.43

 setPassword

0.43

 standards

0.43

 regulations

0.43

 Guidelines

0.40

ervo

0.40

 esterni

0.39

 standard

0.38

GO

0.38

Activations Density 0.093%

references to legal and regulatory entities or frameworks

court rules and guidelines

No Comments

No Known Activations