INDEX

Explanations

political statements and mentions of political figures

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.04

1:0.12

2:0.08

3:0.07

4:0.03

5:0.13

6:0.07

7:0.09

8:0.07

9:0.08

10:0.11

11:0.06

Negative Logits

 organise

-1.30

 realised

-1.27

 colony

-1.27

 neighbourhood

-1.26

 Auckland

-1.23

 recognise

-1.20

 footballer

-1.18

 practise

-1.17

 realise

-1.17

 beginner

-1.16

POSITIVE LOGITS

 Corker

1.68

TRUMP

1.62

politics

1.55

Republicans

1.50

partisan

1.50

GOP

1.49

 Priebus

1.49

 Pelosi

1.48

Trump

1.48

 Politico

1.47

Activations Density 0.397%

political statements and mentions of political figures

No Known Activations