INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

2:0.08

3:0.08

4:0.07

5:0.06

6:0.08

7:0.07

8:0.09

9:0.08

10:0.08

11:0.09

Negative Logits

gem

-2.80

Fa

-2.74

afia

-2.62

 Despair

-2.47

riber

-2.41

wives

-2.34

NRS

-2.32

habi

-2.31

 Salv

-2.29

adle

-2.29

POSITIVE LOGITS

 airborne

2.57

 Bryce

2.49

 Camp

2.45

 astronauts

2.45

 infield

2.43

NASA

2.41

 inadvert

2.39

Air

2.39

 nighttime

2.39

 astronaut

2.38

Activations Density 0.000%

No Known Activations

This feature has no known activations.