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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.09

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

rina

-1.48

................................................................

-1.35

rett

-1.35

agna

-1.34

ograp

-1.34

 GOODMAN

-1.32

ilaterally

-1.31

atin

-1.30

othy

-1.29

 Morse

-1.29

POSITIVE LOGITS

 Cyber

1.36

 Kraken

1.31

pow

1.31

 Goddess

1.29

 Scion

1.29

Khe

1.28

 offline

1.26

cpu

1.25

alore

1.24

href

1.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.