INDEX

Explanations

locations and institutions related to universities and states

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

references to educational institutions and state departments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

0:0.07

1:0.03

2:0.24

3:0.09

4:0.07

5:0.07

6:0.02

7:0.03

8:0.03

9:0.23

10:0.05

11:0.02

Negative Logits

yss

-1.45

 millenn

-1.29

heet

-1.25

 adaptations

-1.23

cients

-1.20

itiveness

-1.20

tera

-1.20

 histories

-1.18

iated

-1.17

iation

-1.15

POSITIVE LOGITS

 caucuses

1.41

Cow

1.27

 Wonderland

1.26

aucuses

1.22

 trooper

1.21

��

1.17

 Rodrig

1.16

1.15

PF

1.15

 Pigs

1.13

Activations Density 0.014%

locations and institutions related to universities and states

references to educational institutions and state departments

No Comments

No Known Activations