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

2:0.08

3:0.09

4:0.09

5:0.08

6:0.08

7:0.07

8:0.09

9:0.08

10:0.07

11:0.07

Negative Logits

 inher

-1.36

 adjud

-1.25

erella

-1.25

 maxim

-1.23

 mistakes

-1.20

 forg

-1.19

 forgiven

-1.19

 transc

-1.16

 MIDI

-1.16

 bypass

-1.16

POSITIVE LOGITS

�

1.76

asio

1.70

SourceFile

1.54

 mosqu

1.52

 corrid

1.49

Rus

1.44

 advoc

1.44

 millenn

1.41

oğ

1.41

 Leban

1.41

Activations Density 0.000%

No Known Activations

This feature has no known activations.