INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.08

2:0.08

3:0.07

4:0.09

5:0.07

6:0.06

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

 Kore

-1.50

Wiki

-1.40

Kos

-1.39

 Recomm

-1.38

pedia

-1.33

 Gear

-1.32

 Phar

-1.31

 Camp

-1.30

 Lank

-1.29

Site

-1.28

POSITIVE LOGITS

emate

1.54

udeau

1.45

anus

1.35

equality

1.29

querque

1.26

andowski

1.25

aiman

1.25

ahime

1.24

imilar

1.24

lando

1.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.