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

1:0.06

2:0.08

3:0.08

4:0.07

5:0.10

6:0.07

7:0.06

8:0.07

9:0.10

10:0.11

11:0.05

Negative Logits

onica

-1.54

 exch

-1.34

alam

-1.34

steamapps

-1.27

sometimes

-1.25

inates

-1.24

cius

-1.23

 neighbours

-1.23

hend

-1.22

holes

-1.21

POSITIVE LOGITS

ONSORED

1.83

 UNCLASSIFIED

1.54

 headlined

1.52

 fielded

1.40

AMA

1.33

 tweeted

1.33

BuyableInstoreAndOnline

1.30

oward

1.30

ifty

1.26

 coverage

1.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.