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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.07

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

inding

-1.47

rade

-1.41

uckle

-1.39

athered

-1.33

vere

-1.32

nn

-1.30

ede

-1.27

este

-1.26

attled

-1.25

isode

-1.24

POSITIVE LOGITS

SourceFile

1.57

═

1.44

 impossibility

1.29

 cumbers

1.29

──

1.29

 Cuomo

1.28

 inaug

1.26

urban

1.25

̶

1.24

Pixel

1.21

Activations Density 0.000%

No Known Activations

This feature has no known activations.