INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.09

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Dorothy

-2.51

……………………

-2.48

requires

-2.48

Dew

-2.46

UTH

-2.45

 Uses

-2.44

½

-2.41

 Freed

-2.40

 Purpose

-2.40

 Alto

-2.40

POSITIVE LOGITS

inka

3.29

 ISIL

3.07

Iraq

2.86

anyahu

2.83

 militar

2.73

 Enix

2.52

gypt

2.49

iphate

2.48

piracy

2.42

ahar

2.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.