INDEX

Explanations

references to high-profile legal cases, particularly involving individuals with notable actions or statements

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

0:0.26

1:0.07

2:0.07

3:0.05

4:0.06

5:0.03

6:0.11

7:0.07

8:0.03

9:0.04

10:0.11

11:0.05

Negative Logits

 Carrier

-4.36

 Dickinson

-4.07

 Meier

-3.73

 Shen

-3.71

 Breast

-3.63

 Rapt

-3.56

 Daniels

-3.50

 Stephenson

-3.48

 Shepherd

-3.45

 Perse

-3.41

POSITIVE LOGITS

 parole

3.61

 exoner

3.36

 burgl

3.35

 cuff

3.30

 handc

3.29

 Simpson

3.22

 burglary

3.16

 gang

3.15

 acquitted

3.15

 holster

3.12

Activations Density 0.000%

references to high-profile legal cases, particularly involving individuals with notable actions or statements

No Known Activations