INDEX

Explanations

legal terms and references related to statutes and evidence

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aarrggbb

-0.66

ILayout

-0.64

parsedMessage

-0.63

MENAFN

-0.60

 protoimpl

-0.58

ContentAsync

-0.58

 MonoBehaviour

-0.57

WaitGroup

-0.56

 unknownFields

-0.56

ward

-0.54

POSITIVE LOGITS

 Statute

0.61

 laws

0.60

 rules

0.59

law

0.57

 Statutes

0.57

 Rules

0.56

Gambas

0.55

 statutes

0.55

 rule

0.53

 statute

0.53

Activations Density 0.735%

legal terms and references related to statutes and evidence

No Comments

No Known Activations