INDEX

Explanations

phrases related to surveillance and monitoring activities

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

0:0.02

1:0.01

2:0.08

3:0.05

4:0.05

5:0.03

6:0.29

7:0.05

8:0.04

9:0.04

10:0.19

11:0.11

Negative Logits

ividual

-1.43

BuyableInstoreAndOnline

-1.32

�

-1.26

oway

-1.24

 proud

-1.23

ufact

-1.22

ierre

-1.21

 empath

-1.17

アル

-1.15

Ez

-1.13

POSITIVE LOGITS

lation

1.27

illance

1.22

 Spur

1.16

 Prompt

1.15

 giveaways

1.12

yahoo

1.11

 Prel

1.10

 Sear

1.10

rams

1.09

cuts

1.08

Activations Density 0.003%

phrases related to surveillance and monitoring activities

No Comments

No Known Activations