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

1:0.08

2:0.08

3:0.09

4:0.08

5:0.09

6:0.08

7:0.09

8:0.08

9:0.07

10:0.07

11:0.07

Negative Logits

 cards

-1.44

 titles

-1.42

 classics

-1.41

 Highlights

-1.38

WN

-1.37

 Cards

-1.35

 Stamp

-1.33

 Monthly

-1.33

 Numbers

-1.31

 Dates

-1.28

POSITIVE LOGITS

\\\\\\\\

1.76

externalActionCode

1.68

)].

1.67

FORE

1.61

anooga

1.59

asin

1.53

zona

1.52

////////

1.50

isol

1.49

furt

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.