INDEX

Explanations

numerical measurements and units

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

0:0.12

1:0.03

2:0.29

3:0.06

4:0.07

5:0.05

6:0.06

7:0.03

8:0.07

9:0.08

10:0.06

11:0.02

Negative Logits

gnu

-1.56

Balance

-1.41

byss

-1.30

 Democr

-1.20

iannopoulos

-1.17

ende

-1.16

 Chains

-1.16

adr

-1.16

ween

-1.14

allows

-1.13

POSITIVE LOGITS

 Introduction

1.39

��

1.34

[+

1.33

ciplinary

1.25

flix

1.21

Ago

1.20

rss

1.20

appa

1.20

genic

1.20

apo

1.18

Activations Density 0.029%

numerical measurements and units

No Comments

No Known Activations