INDEX

Explanations

information related to population statistics and demographic changes

New Auto-Interp

Top Features by Cosine Similarity

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

2:0.07

3:0.06

4:0.05

5:0.07

6:0.04

7:0.06

8:0.04

9:0.06

10:0.34

11:0.12

Negative Logits

 patent

-1.68

 Patent

-1.62

 patents

-1.60

 DMCA

-1.58

 trademarks

-1.58

 retracted

-1.53

 takedown

-1.53

endiary

-1.52

 retract

-1.51

 plagiar

-1.51

POSITIVE LOGITS

population

2.19

Population

2.10

 population

1.74

 demographic

1.63

 demographics

1.56

 subsistence

1.52

occup

1.51

 inhab

1.50

Occup

1.45

Numbers

1.42

Activations Density 0.039%

information related to population statistics and demographic changes

No Known Activations