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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.06

2:0.07

3:0.09

4:0.08

5:0.09

6:0.07

7:0.07

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

tac

-1.56

agra

-1.45

atin

-1.40

 Keystone

-1.40

airo

-1.33

snap

-1.29

 Gadget

-1.26

FRE

-1.24

ctuary

-1.23

GO

-1.23

POSITIVE LOGITS

 Azerbaijan

1.41

uke

1.39

 allowance

1.37

 contingent

1.32

henko

1.29

imester

1.29

nikov

1.28

eva

1.25

undai

1.22

 Ibrahim

1.22

Activations Density 0.000%

No Known Activations

This feature has no known activations.