INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.08

1:0.03

2:0.28

3:0.06

4:0.16

5:0.05

6:0.03

7:0.03

8:0.06

9:0.10

10:0.04

11:0.02

Negative Logits

 Cros

-1.52

coe

-1.41

aminer

-1.31

akespeare

-1.30

anwhile

-1.29

sworth

-1.25

espie

-1.24

netflix

-1.24

chat

-1.22

pret

-1.17

POSITIVE LOGITS

League

1.42

Eastern

1.42

Magikarp

1.36

Daw

1.28

Buk

1.27

Lago

1.25

 Chiefs

1.24

————

1.23

Sek

1.19

insk

1.18

Activations Density 0.002%

names of individuals

No Comments

No Known Activations