INDEX

Explanations

astrological signs, names, and abbreviations

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

references to specific individuals or families involved in legal issues, particularly concerning public assistance

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

0:0.02

1:0.04

2:0.06

3:0.32

4:0.02

5:0.03

6:0.06

7:0.14

8:0.07

9:0.07

10:0.04

11:0.08

Negative Logits

 conclud

-1.34

kefeller

-1.31

ICLE

-1.29

theless

-1.27

glomer

-1.27

 skelet

-1.27

 Brock

-1.22

 Bronx

-1.20

エル

-1.17

 Guerrero

-1.16

POSITIVE LOGITS

iasis

1.62

nikov

1.49

oin

1.37

 Offer

1.23

 Practices

1.21

oji

1.20

 ideals

1.17

ignty

1.16

arma

1.15

arov

1.14

Activations Density 0.010%

astrological signs, names, and abbreviations

references to specific individuals or families involved in legal issues, particularly concerning public assistance

No Comments

No Known Activations