INDEX

Explanations

No Explanations Found

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

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.08

2:0.07

3:0.07

4:0.07

5:0.08

6:0.09

7:0.08

8:0.07

9:0.08

10:0.08

11:0.07

Negative Logits

abama

-2.64

usc

-2.60

 Dover

-2.54

querade

-2.53

abbage

-2.51

annabin

-2.50

 attm

-2.48

ertodd

-2.40

ologne

-2.38

actus

-2.35

POSITIVE LOGITS

 Vive

2.56

.�

2.42

Omn

2.41

 swapped

2.38

 orange

2.33

assetsadobe

2.33

 Copy

2.32

 Zucker

2.31

orean

2.30

 Raptors

2.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.