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

0:0.09

1:0.07

2:0.10

3:0.07

4:0.08

5:0.08

6:0.07

7:0.07

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

 Wellington

-1.47

ignt

-1.40

merce

-1.39

 throne

-1.38

 Cors

-1.22

 Temper

-1.21

 Somerset

-1.20

 Hornets

-1.20

 Militia

-1.20

ounty

-1.17

POSITIVE LOGITS

═

1.40

ItemThumbnailImage

1.36

zy

1.35

zan

1.29

amer

1.28

�

1.26

Interstitial

1.19

Context

1.18

actionDate

1.17

 Reported

1.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.