INDEX

Explanations

legal terminology related to criminal charges and offenses

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

legal charges or counts

np_acts-logits-general · gemini-2.0-flash

charges and counts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

InjectAttribute

-0.71

ParallelGroup

-0.63

IUrlHelper

-0.57

Gön

-0.50

RefNanny

-0.50

 AssemblyCulture

-0.49

 Ause

-0.48

Referències

-0.48

Datuak

-0.47

 dynamic

-0.47

POSITIVE LOGITS

 charges

2.22

 charge

1.88

 Charges

1.84

Charges

1.74

 charged

1.63

charges

1.62

 Charge

1.61

Charge

1.54

charge

1.53

 CHARGE

1.45

Activations Density 0.382%

legal terminology related to criminal charges and offenses

legal charges or counts

charges and counts

No Comments

No Known Activations