INDEX

Explanations

phrases related to significant historical events and figures

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

0:0.07

1:0.02

2:0.10

3:0.08

4:0.02

5:0.07

6:0.05

7:0.09

8:0.31

9:0.05

10:0.04

11:0.04

Negative Logits

 Catalyst

-3.43

ajor

-3.15

arijuana

-3.12

 Holder

-3.11

WB

-3.10

////////////////

-3.05

 Gilmore

-3.04

reen

-3.04

}{

-3.02

CBD

-2.98

POSITIVE LOGITS

 Napoleon

6.95

Nap

4.80

 Frenchman

4.39

 Trotsky

4.27

 Bolshe

4.18

 Mongolia

4.17

 Mongol

4.06

 Stalin

3.98

 Alps

3.90

oleon

3.88

Activations Density 0.001%

phrases related to significant historical events and figures

No Known Activations