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

0:0.09

1:0.09

2:0.09

3:0.08

4:0.07

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

iband

-1.41

ndum

-1.31

 beginner

-1.28

 fluoride

-1.27

 medicinal

-1.25

 antib

-1.25

cpu

-1.25

 macro

-1.23

Phys

-1.22

 beginners

-1.19

POSITIVE LOGITS

 WATCHED

1.43

 Antar

1.40

etheless

1.37

abre

1.37

dar

1.36

 Deaths

1.32

anwhile

1.32

 Dating

1.32

script

1.30

argon

1.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.