INDEX

Explanations

statements related to gender equality and bias in various fields, including tech, math, and the perception of women and men in society

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

0:0.07

1:0.07

2:0.11

3:0.08

4:0.02

5:0.08

6:0.04

7:0.07

8:0.04

9:0.19

10:0.13

11:0.05

Negative Logits

版

-1.44

Site

-1.43

ridor

-1.28

MAP

-1.27

NEWS

-1.19

Opening

-1.18

FUN

-1.17

nit

-1.16

IFF

-1.16

Battery

-1.14

POSITIVE LOGITS

 circumcised

1.42

 respectively

1.41

 sexes

1.38

pees

1.37

joice

1.37

��

1.35

 themselves

1.31

gyn

1.30

selves

1.27

 willingly

1.26

Activations Density 0.127%

statements related to gender equality and bias in various fields, including tech, math, and the perception of women and men in society

No Known Activations