INDEX

Explanations

legal references and terminology related to court cases and judicial rulings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

COUVER

-0.80

 BoxFit

-0.71

MLLoader

-0.71

 Obrador

-0.70

Geplaatst

-0.68



-0.65

 alpina

-0.64

 TORONTO

-0.64

esgue

-0.63

 betweenstory

-0.61

POSITIVE LOGITS

 Alabama

0.74

 Mississippi

0.69

Alabama

0.64

 Carolina

0.64

 Bama

0.62

Mississippi

0.60

issippi

0.59

 Southern

0.59

 Macon

0.58

 Georgia

0.56

Activations Density 0.705%

legal references and terminology related to court cases and judicial rulings

No Comments

No Known Activations