INDEX

Explanations

legal terminology and references to court cases and decisions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setupUi

-0.87

 rhestr

-0.69

XtraGrid

-0.68

ViewFeatures

-0.66

 ModelExpression

-0.65

الحياه

-0.65

canActivate

-0.62



-0.61

 AssemblyCulture

-0.61

Sklici

-0.61

POSITIVE LOGITS

 precedent

0.69

 precedents

0.61

 appellate

0.54

 jurisprudence

0.52

 cases

0.52

case

0.51

 Appellate

0.51

 Appeals

0.51

 ruling

0.51

Cases

0.50

Activations Density 2.417%

legal terminology and references to court cases and decisions

No Comments

No Known Activations