INDEX

Explanations

references to political parties and their actions or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.26

1:0.04

2:0.02

3:0.10

4:0.06

5:0.01

6:0.07

7:0.14

8:0.02

9:0.03

10:0.16

11:0.03

Negative Logits

LSU

-3.49

Nintendo

-3.39

 Clemson

-3.36

uterte

-3.25

 Baton

-3.22

Wii

-3.17

 Raptors

-3.16

Alabama

-3.13

 Halo

-3.07

 Reggie

-3.05

POSITIVE LOGITS

 Austrian

7.82

 Austria

7.71

Aust

7.37

 Vienna

7.23

 Aust

6.42

Hung

5.14

Ö

4.91

 Hungarian

4.90

 Hungary

4.89

 Budapest

4.66

Activations Density 0.021%

references to political parties and their actions or statements

No Comments

No Known Activations