INDEX

Explanations

numerical values and time-related measurements

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

0:0.02

1:0.02

2:0.11

3:0.03

4:0.08

5:0.02

6:0.37

7:0.06

8:0.03

9:0.03

10:0.09

11:0.06

Negative Logits

erning

-1.50

artisan

-1.41

 tracts

-1.37

erto

-1.29

uct

-1.27

uador

-1.25

bilt

-1.19

anche

-1.18

Sax

-1.17

reon

-1.16

POSITIVE LOGITS

Cooldown

1.56

rush

1.50

 elapsed

1.31

imposed

1.19

 Shots

1.18

 Width

1.16

instead

1.16

 Destination

1.15

Huh

1.13

 Refresh

1.13

Activations Density 0.053%

numerical values and time-related measurements

No Known Activations