INDEX

Explanations

terms related to authentication and authorization processes

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

0:0.04

1:0.04

2:0.07

3:0.12

4:0.04

5:0.05

6:0.12

7:0.22

8:0.05

9:0.06

10:0.08

11:0.07

Negative Logits

achus

-1.40

姫

-1.38

xual

-1.33

terson

-1.28

enburg

-1.24

hatt

-1.21

wcs

-1.17

ibaba

-1.17

cipline

-1.16

imeters

-1.15

POSITIVE LOGITS

VO

1.21

 Presence

1.17

 Authorization

1.05

 password

1.04

RAW

1.03

 verified

1.03

 credentials

1.02

CE

1.01

 authentication

1.01

 faked

0.97

Activations Density 0.014%

terms related to authentication and authorization processes

No Comments

No Known Activations