INDEX

Explanations

descriptions of outfits and clothing items

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

Head Attr Weights

0:0.06

1:0.07

2:0.05

3:0.04

4:0.22

5:0.04

6:0.03

7:0.17

8:0.02

9:0.07

10:0.06

11:0.12

Negative Logits

Solution

-3.29

[_

-2.83

ovie

-2.57

 Solution

-2.56

 Solutions

-2.53

olutions

-2.50

ITNESS

-2.42

Valid

-2.32

agents

-2.30

¯

-2.29

POSITIVE LOGITS

 crimson

3.32

 golden

3.13

 pale

2.92

 velvet

2.80

 yellow

2.79

 grey

2.78

 blond

2.77

 curls

2.76

 curly

2.69

 green

2.68

Activations Density 0.096%

descriptions of outfits and clothing items

No Known Activations