INDEX

Explanations

technical terms related to electrical engineering, particularly focusing on voltage and current measurements

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Head Attr Weights

0:0.05

1:0.04

2:0.07

3:0.11

4:0.06

5:0.06

6:0.07

7:0.26

8:0.06

9:0.04

10:0.07

11:0.06

Negative Logits

actionDate

-1.63

生

-1.22

ername

-1.21

カ

-1.20

 largeDownload

-1.20

 confession

-1.17

 Negro

-1.15

�

-1.15

��

-1.12

王

-1.12

POSITIVE LOGITS

 tubing

1.35

 phosph

1.33

 batteries

1.31

aline

1.28

intensity

1.28

 throughput

1.27

 downstream

1.26

 drain

1.26

 propulsion

1.26

 LEDs

1.24

Activations Density 0.006%

technical terms related to electrical engineering, particularly focusing on voltage and current measurements

No Known Activations