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

0:0.09

1:0.07

2:0.09

3:0.08

4:0.07

5:0.08

6:0.08

7:0.06

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

raltar

-2.00

maxwell

-2.00

redo

-1.70

arij

-1.66

igrants

-1.66

jri

-1.54

uador

-1.54

igrant

-1.52

schild

-1.49

orage

-1.49

POSITIVE LOGITS

 twitch

1.76

 Costume

1.43

scenes

1.42

 Mankind

1.41

 climax

1.39

".[

1.34

 nails

1.32

 films

1.31

 otherwise

1.30

 Beacon

1.28

Activations Density 0.000%

No Known Activations

This feature has no known activations.