INDEX

Explanations

characteristics and descriptions of flowers, including their physical traits and structural elements

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

0:0.33

1:0.02

2:0.12

3:0.13

4:0.03

5:0.07

6:0.06

7:0.05

8:0.04

9:0.03

10:0.04

11:0.03

Negative Logits

Gaming

-3.45

 Gaming

-3.02

 gaming

-2.85

 Shack

-2.83

Gamer

-2.82

ORPG

-2.81

Mach

-2.80

 gamers

-2.79

 PlayStation

-2.76

 casinos

-2.75

POSITIVE LOGITS

 flowers

6.18

 flower

5.50

 roses

5.29

 floral

4.99

 Flowers

4.56

flower

4.56

 bloom

4.47

bou

4.32

 flowering

4.13

blo

3.92

Activations Density 0.028%

characteristics and descriptions of flowers, including their physical traits and structural elements

No Known Activations