INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.10

2:0.07

3:0.09

4:0.08

5:0.07

6:0.08

7:0.07

8:0.08

9:0.08

10:0.08

11:0.09

Negative Logits

olo

-1.61

Documents

-1.56

=~

-1.50

 Delete

-1.49

QC

-1.47

 Flavoring

-1.46

riter

-1.41

 Hilton

-1.38

 Printed

-1.38

olded

-1.37

POSITIVE LOGITS

 Pigs

1.74

 coup

1.66

 Chero

1.66

inav

1.62

bas

1.62

 ende

1.56

furt

1.56

erest

1.55

 Coup

1.55

 Pengu

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.