INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.07

2:0.09

3:0.08

4:0.09

5:0.07

6:0.09

7:0.07

8:0.09

9:0.07

10:0.08

11:0.07

Negative Logits

amn

-1.68

Boot

-1.63

fecture

-1.61

 Isles

-1.58

 retirement

-1.52

 deserted

-1.48

 Throne

-1.44

 Settlement

-1.43

luck

-1.40

 Luck

-1.40

POSITIVE LOGITS

1.83

 outweigh

1.59

 Dictionary

1.55

assetsadobe

1.53

alsh

1.51

ctions

1.50

 rake

1.49

 staples

1.46

cules

1.45

WARE

1.43

Activations Density 0.000%

No Known Activations

This feature has no known activations.