INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

0:0.08

1:0.07

2:0.08

3:0.08

4:0.07

5:0.09

6:0.09

7:0.07

8:0.07

9:0.07

10:0.08

11:0.09

Negative Logits

 lapt

-1.53

pes

-1.42

 vain

-1.41

arten

-1.36

 gloom

-1.29

WOR

-1.29

 accus

-1.25

dry

-1.24

 tort

-1.23

 pregn

-1.23

POSITIVE LOGITS

 Franch

1.55

FTWARE

1.55

hei

1.36

 Battalion

1.35

 DRAG

1.35

ential

1.29

haar

1.28

 Overwatch

1.25

 Helm

1.24

autical

1.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.