INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.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

1:0.09

2:0.07

3:0.08

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

 folds

-1.38

 formulations

-1.36

olor

-1.34

Shape

-1.27

([

-1.23

missible

-1.23

ilogy

-1.22

 manifests

-1.21

 yields

-1.20

ulates

-1.20

POSITIVE LOGITS

apist

1.44

zee

1.40

 curiosity

1.37

 metic

1.33

 Militia

1.32

 Gupta

1.31

swer

1.28

 whim

1.28

zees

1.27

 curfew

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.