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

1:0.06

2:0.09

3:0.10

4:0.07

5:0.08

6:0.07

7:0.08

8:0.08

9:0.06

10:0.08

11:0.08

Negative Logits

Poké

-2.63

icious

-2.56

keyes

-2.45

Requ

-2.43

 indoors

-2.42

��

-2.41

BUG

-2.36

apply

-2.35

acle

-2.32

ho

-2.31

POSITIVE LOGITS

 Cantor

2.60

 Shelby

2.50

 Rothschild

2.38

 Ruth

2.36

 Ford

2.33

 Barrett

2.32

 Woodward

2.31

 coffers

2.30

 Wendy

2.29

 Sutherland

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.