INDEX

Explanations

phrases indicating authority or governance

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.03

1:0.02

2:0.12

3:0.10

4:0.11

5:0.04

6:0.26

7:0.05

8:0.04

9:0.07

10:0.06

11:0.05

Negative Logits

 advoc

-1.56

 Olymp

-1.32

 surpr

-1.23

Buc

-1.20

 Malt

-1.17

 Paraly

-1.14

 inval

-1.11

LOD

-1.11

 Berm

-1.09

 Bones

-1.07

POSITIVE LOGITS

reply

1.54

MSN

1.48

SpaceEngineers

1.41

outed

1.35

ongyang

1.33

ournament

1.31

orea

1.30

assetsadobe

1.27

Downloadha

1.24

reetings

1.20

Activations Density 0.006%

phrases indicating authority or governance

No Comments

No Known Activations