INDEX

Explanations

data related to homicide rates and crime statistics

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.15

1:0.06

2:0.06

3:0.09

4:0.06

5:0.02

6:0.09

7:0.15

8:0.03

9:0.05

10:0.09

11:0.11

Negative Logits

 Protoss

-3.07

ESA

-2.73

 Chess

-2.73

 Airbus

-2.70

 Frieza

-2.63

 Telescope

-2.55

 eSports

-2.52

 Zerg

-2.49

 Cricket

-2.47

 Starcraft

-2.45

POSITIVE LOGITS

 homicides

3.38

 Murd

3.19

buquerque

3.06

 murders

3.05

 homicide

2.96

 Blasio

2.76

 Killer

2.67

Mayor

2.65

 shootings

2.63

 mayoral

2.62

Activations Density 0.005%

data related to homicide rates and crime statistics

No Known Activations