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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.09

8:0.07

9:0.08

10:0.08

11:0.08

Negative Logits

ibaba

-3.08

��

-3.05

uador

-2.84

ゴ

-2.74

��

-2.68

 vert

-2.66

swing

-2.58

�

-2.57

assic

-2.52

 itch

-2.51

POSITIVE LOGITS

 Crusade

2.92

 inscribed

2.82

 Commission

2.74

 Letter

2.58

LC

2.42

 Favor

2.41

 Prohibition

2.39

Pie

2.34

 Chapter

2.33

 vetoed

2.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.