INDEX

Explanations

phrases and terms related to safety and security

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

0:0.01

1:0.01

2:0.09

3:0.05

4:0.04

5:0.02

6:0.43

7:0.07

8:0.03

9:0.03

10:0.09

11:0.07

Negative Logits

govtrack

-1.75

minus

-1.65

 sugg

-1.59

-1.50

ividual

-1.48

��

-1.36

assadors

-1.35

axter

-1.34

incial

-1.29

uably

-1.28

POSITIVE LOGITS

Applic

1.48

 Ends

1.35

 Sounds

1.33

 Sound

1.29

Fax

1.23

 Networks

1.21

 Horn

1.19

VPN

1.16

 Warriors

1.15

 Chim

1.15

Activations Density 0.008%

phrases and terms related to safety and security

No Comments

No Known Activations