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

0:0.06

1:0.08

2:0.08

3:0.07

4:0.07

5:0.09

6:0.09

7:0.08

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

ebted

-1.41

Riy

-1.41

 Winc

-1.36

enza

-1.34

Nep

-1.34

phia

-1.28

leep

-1.26

hematic

-1.25

 owes

-1.24

igi

-1.24

POSITIVE LOGITS

EStream

1.54

ullivan

1.52

 Topic

1.40

 Carson

1.39

](

1.36

uer

1.34

soType

1.30

 discouraging

1.30

AZ

1.28

��

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.