INDEX

Explanations

names of heroes or individuals being praised

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

0:0.05

1:0.05

2:0.14

3:0.06

4:0.04

5:0.10

6:0.03

7:0.04

8:0.05

9:0.26

10:0.08

11:0.03

Negative Logits

Downloadha

-1.40

rastructure

-1.27

iliar

-1.27

 equivalents

-1.26

 vacancies

-1.24

insured

-1.23

abus

-1.21

 diploma

-1.20

unicip

-1.20

rupal

-1.20

POSITIVE LOGITS

 Mara

1.59

 Yamato

1.46

 Scully

1.42

venge

1.40

 Luffy

1.40

 Monstrous

1.37

 Nebula

1.36

Kl

1.30

Nek

1.30

Ko

1.30

Activations Density 0.029%

names of heroes or individuals being praised

No Comments

No Known Activations