INDEX

Explanations

words related to women's rights, particularly in politics and society

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

mentions of women and their roles, rights, and representation in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.07

2:0.08

3:0.08

4:0.03

5:0.09

6:0.03

7:0.05

8:0.04

9:0.24

10:0.11

11:0.06

Negative Logits

 Router

-1.47

erous

-1.35

 Products

-1.28

 Definitions

-1.27

 Diver

-1.24

 Repeat

-1.24

 Wast

-1.24

 Vapor

-1.23

 Contents

-1.21

ciation

-1.20

POSITIVE LOGITS

 hijab

1.71

 menstru

1.57

 circumcised

1.56

 whom

1.55

 nurse

1.44

ozyg

1.40

Eva

1.40

deen

1.38

 raped

1.37

 oppressed

1.35

Activations Density 0.168%

words related to women's rights, particularly in politics and society

mentions of women and their roles, rights, and representation in various contexts

No Comments

No Known Activations