INDEX

Explanations

references to regulations and their impact on individuals or groups

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

2:0.23

3:0.20

4:0.15

5:0.03

6:0.03

7:0.09

8:0.05

9:0.03

10:0.05

11:0.06

Negative Logits

す

-1.64

eeee

-1.42

 tempered

-1.40

 shoulders

-1.34

 inev

-1.32

 Incarn

-1.29

 CHRIST

-1.28

 aven

-1.27

terness

-1.26

 Hawai

-1.26

POSITIVE LOGITS

 showc

1.62

 were

1.53

unia

1.51

 include

1.48

idates

1.42

 originate

1.39

ials

1.37

@@

1.35

were

1.34

are

1.34

Activations Density 0.191%

references to regulations and their impact on individuals or groups

No Comments

No Known Activations