INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.07

1:0.08

2:0.07

3:0.08

4:0.08

5:0.09

6:0.09

7:0.09

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

Race

-1.27

 Advertisement

-1.22

 Matter

-1.17

 Surveillance

-1.17

 Statement

-1.16

Nap

-1.16

gment

-1.15

Join

-1.14

 Relationship

-1.13

 Porn

-1.13

POSITIVE LOGITS

�

1.41

anwhile

1.33

zbek

1.31

)."

1.27

@#&

1.26

)"

1.21

 streng

1.20

tails

1.18

raid

1.17

%]

1.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.