INDEX

Explanations

topics or keywords related to news and articles, potentially related to crime, politics, or industry

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

topics related to health and wellness issues

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

1:0.04

2:0.13

3:0.08

4:0.22

5:0.05

6:0.05

7:0.03

8:0.10

9:0.09

10:0.06

11:0.02

Negative Logits

tein

-1.36

icidal

-1.26

lite

-1.18

USD

-1.16

bley

-1.15

athing

-1.14

adra

-1.14

APTER

-1.11

AGES

-1.10

cit

-1.09

POSITIVE LOGITS

 millenn

1.56

 Questions

1.31

Fact

1.29

Shar

1.24

iosyncr

1.21

 unden

1.20

cius

1.20

anwhile

1.19

 Diseases

1.16

 Topic

1.14

Activations Density 0.002%

topics or keywords related to news and articles, potentially related to crime, politics, or industry

topics related to health and wellness issues

No Comments

No Known Activations