INDEX

Explanations

concepts related to structures of society and governance

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

0:0.18

1:0.19

2:0.06

3:0.04

4:0.03

5:0.02

6:0.07

7:0.10

8:0.02

9:0.04

10:0.15

11:0.04

Negative Logits

ディ

-3.12

Tid

-3.05

 Blades

-2.89

フォ

-2.85

hiba

-2.83

ヴァ

-2.75

orsi

-2.73

Fel

-2.71

ォ

-2.70

ザ

-2.64

POSITIVE LOGITS

Hop

8.25

Hop

7.97

hop

7.37

 hops

6.34

hop

5.59

 hopping

5.30

 hopped

4.77

hops

4.59

Hip

4.05

Ho

4.01

Activations Density 0.004%

concepts related to structures of society and governance

No Known Activations