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

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.09

Negative Logits

osed

-1.40

Rated

-1.39

edIn

-1.38

 srfAttach

-1.38

ormon

-1.36

 Plaint

-1.27

rawdownloadcloneembedreportprint

-1.27

quished

-1.25

atto

-1.20

agin

-1.20

POSITIVE LOGITS

isphere

1.59

argon

1.51

mine

1.48

 excludes

1.40

 subsid

1.27

 quir

1.23

lance

1.22

unia

1.22

gmail

1.21

 Carney

1.19

Activations Density 0.000%

No Known Activations

This feature has no known activations.