INDEX

Explanations

concepts related to dystopian themes and scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

0:0.04

1:0.03

2:0.04

3:0.09

4:0.03

5:0.04

6:0.14

7:0.20

8:0.04

9:0.04

10:0.11

11:0.15

Negative Logits

 dues

-1.42

igham

-1.33

 disciplined

-1.25

 referral

-1.24

ioch

-1.24

verning

-1.21

 referrals

-1.19

xual

-1.18

NEY

-1.17

ONY

-1.16

POSITIVE LOGITS

 Ultron

1.51

 gloom

1.48

 Purg

1.42

 backdrop

1.36

 Apocalypse

1.23

 apocalyptic

1.23

 apocalypse

1.22

 Horror

1.21

 dystop

1.20

 dystopian

1.18

Activations Density 0.009%

concepts related to dystopian themes and scenarios

No Comments

No Known Activations