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

1:0.08

2:0.09

3:0.08

4:0.08

5:0.07

6:0.07

7:0.07

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

 branches

-1.39

packing

-1.37

utherford

-1.30

oots

-1.30

 penet

-1.26

 disp

-1.20

andom

-1.19

 drip

-1.19

flo

-1.18

Tea

-1.18

POSITIVE LOGITS

 Shutterstock

1.62

 Liberties

1.53

andowski

1.44

ickr

1.40

abus

1.40

utterstock

1.39

 notwithstanding

1.38

 Mous

1.35

nea

1.34

oğ

1.33

Activations Density 0.000%

No Known Activations

This feature has no known activations.