INDEX

Explanations

references to monetary amounts and fundraising activities

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

0:0.02

1:0.01

2:0.09

3:0.08

4:0.11

5:0.03

6:0.05

7:0.10

8:0.04

9:0.04

10:0.27

11:0.11

Negative Logits

opathy

-1.50

 Redux

-1.41

î

-1.35

imil

-1.34

 differe

-1.23

 deterior

-1.22

 lapse

-1.21

��

-1.20

 replaced

-1.20

resy

-1.20

POSITIVE LOGITS

 backers

1.60

 pledged

1.53

 pledges

1.52

 donors

1.52

 hopes

1.51

 Sparks

1.47

 fundraising

1.43

 seed

1.42

 donations

1.36

 organizers

1.36

Activations Density 0.031%

references to monetary amounts and fundraising activities

No Known Activations