INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.08

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.07

10:0.09

11:0.08

Negative Logits

 Berm

-3.38

 Clone

-3.03

Dot

-2.81

 Ster

-2.78

 Arbit

-2.70

 Copyright

-2.53

Zer

-2.53

cop

-2.53

ック

-2.52

 Stard

-2.45

POSITIVE LOGITS

ovo

3.00

î

2.56

izo

2.51

 sane

2.48

 cred

2.45

 CHRIST

2.38

inct

2.33

 shepherd

2.33

viz

2.33

adian

2.30

Activations Density 0.000%

No Known Activations

This feature has no known activations.