INDEX

Explanations

legal terminology and references

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

Legal case citations

np_acts-logits-general · gemini-2.0-flash

United States District Court

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

 hook

-0.39

 imagining

-0.35

 derail

-0.34

 deduction

-0.33

yaf

-0.32

 IConfiguration

-0.32

 uproar

-0.32

 kolei

-0.32

 itemView

-0.31

nalités

-0.31

POSITIVE LOGITS

 autorytatywna

0.60

GEBURTS

0.60

 estekak

0.58

IUrlHelper

0.56

windowFixed

0.56

 surla

0.56

@"/

0.54

 ProtoMessage

0.53

ⓧ

0.52

 ویکی‌پدی

0.52

Activations Density 0.554%

legal terminology and references

Legal case citations

United States District Court

No Comments

No Known Activations