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

Head Attr Weights

0:0.09

1:0.08

2:0.07

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.07

9:0.08

10:0.07

11:0.09

Negative Logits

 typew

-1.65

represented

-1.60

established

-1.45

cad

-1.42

 Sabbath

-1.39

ailable

-1.34

issued

-1.33

 skelet

-1.31

stroke

-1.29

 parole

-1.28

POSITIVE LOGITS

 guiName

1.97

udeau

1.50

ghai

1.50

anian

1.49

eus

1.48

 Picture

1.48

 Thumbnails

1.46

 Flickr

1.44

 Links

1.41

nexus

1.39

Activations Density 0.000%

No Known Activations

This feature has no known activations.