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

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.08

2:0.08

3:0.08

4:0.08

5:0.09

6:0.07

7:0.06

8:0.09

9:0.08

10:0.07

11:0.10

Negative Logits

bench

-1.42

 Duty

-1.35

sylv

-1.33

 lockdown

-1.32

 seat

-1.30

 barracks

-1.28

 hiber

-1.26

arij

-1.26

 Turn

-1.25

pac

-1.22

POSITIVE LOGITS

BIT

1.70

xual

1.65

etheless

1.59

%:

1.44

TPS

1.44

leness

1.44

ESCO

1.44

};

1.43

ONEY

1.40

*/

1.40

Activations Density 0.000%

No Known Activations

This feature has no known activations.