INDEX

Explanations

phrases related to loading or positioning items

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

verbs related to loading or transporting items

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.01

1:0.02

2:0.08

3:0.09

4:0.01

5:0.05

6:0.05

7:0.07

8:0.09

9:0.32

10:0.07

11:0.09

Negative Logits

xual

-1.53

hig

-1.35

Gamer

-1.33

acea

-1.30

ongevity

-1.29

etheless

-1.22

utenberg

-1.18

lege

-1.15

aved

-1.13

mean

-1.12

POSITIVE LOGITS

 ships

1.26

 load

1.23

 loaded

1.21

 popcorn

1.16

 containers

1.15

 tray

1.13

redients

1.13

 filters

1.12

 loads

1.11

 Romeo

1.10

Activations Density 0.008%

phrases related to loading or positioning items

verbs related to loading or transporting items

No Comments

No Known Activations