INDEX

Explanations

names and terms related to research organizations and projects, especially in the field of energy research

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

1:0.04

2:0.15

3:0.12

4:0.20

5:0.04

6:0.02

7:0.02

8:0.09

9:0.14

10:0.05

11:0.02

Negative Logits

afa

-1.35

isSpecialOrderable

-1.34

bley

-1.33

endi

-1.29

ickle

-1.27

 Luxem

-1.24

lain

-1.24

yk

-1.23

atu

-1.22

ieth

-1.21

POSITIVE LOGITS

 Telescope

1.58

 Technician

1.38

 Imaging

1.36

 Technology

1.36

uctor

1.33

 Advanced

1.32

 pursuits

1.30

 Format

1.29

 Simulator

1.28

Advanced

1.27

Activations Density 0.004%

names and terms related to research organizations and projects, especially in the field of energy research

No Comments

No Known Activations