INDEX

Explanations

references to blockchain governance and technology

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

1:0.02

2:0.08

3:0.06

4:0.04

5:0.03

6:0.36

7:0.03

8:0.03

9:0.03

10:0.14

11:0.11

Negative Logits

 Pradesh

-1.52

aska

-1.27

iaries

-1.26

DAY

-1.26

 Patron

-1.25

andise

-1.23

iary

-1.18

 complains

-1.18

{*

-1.18

yip

-1.17

POSITIVE LOGITS

modules

1.64

aligned

1.51

士

1.37

バ

1.27

engineering

1.27

integ

1.27

龍契士

1.26

platform

1.26

vention

1.26

headers

1.24

Activations Density 0.005%

references to blockchain governance and technology

No Known Activations