INDEX

Explanations

terms related to social policies and structures

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.03

1:0.01

2:0.24

3:0.10

4:0.22

5:0.02

6:0.16

7:0.03

8:0.04

9:0.02

10:0.03

11:0.04

Negative Logits

ocide

-1.34

 itch

-1.27

д

-1.25

�

-1.23

 sunset

-1.23

pow

-1.22

CY

-1.20

ドラゴン

-1.19

HB

-1.17

 Kosovo

-1.16

POSITIVE LOGITS

staking

1.73

ctors

1.50

etheless

1.48

quartered

1.47

 alike

1.38

 themselves

1.34

hari

1.33

 speculate

1.31

agher

1.30

theless

1.29

Activations Density 0.052%

terms related to social policies and structures

No Known Activations