INDEX

Explanations

references to rules or legal frameworks concerning governance or policy

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

0:0.03

1:0.02

2:0.02

3:0.04

4:0.07

5:0.04

6:0.04

7:0.05

8:0.02

9:0.14

10:0.02

11:0.47

Negative Logits

hell

-2.55

endar

-2.26

wra

-2.18

osaurs

-2.13

 Piercing

-2.11

wrap

-2.11

opus

-2.10

agues

-2.08

vous

-2.07

gallery

-2.03

POSITIVE LOGITS

 grounds

4.14

 merits

3.71

 basis

3.57

 terms

3.27

 principles

3.27

 pretext

3.19

 footing

3.19

 criteria

3.11

issues

3.08

 behalf

2.96

Activations Density 0.096%

references to rules or legal frameworks concerning governance or policy

No Known Activations