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

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.08

2:0.08

3:0.07

4:0.08

5:0.09

6:0.08

7:0.08

8:0.09

9:0.09

10:0.07

11:0.08

Negative Logits

athi

-1.54

Iss

-1.43

arette

-1.40

 Citizen

-1.38

Safety

-1.37

enza

-1.32

ologue

-1.31

Reviewer

-1.27

eenth

-1.27

Characters

-1.27

POSITIVE LOGITS

udeau

1.80

bourg

1.42

 Sturgeon

1.35

 quoting

1.33

 Marketable

1.32

 embr

1.31

debian

1.30

ahoo

1.30

 Trog

1.29

 harbour

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.