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

1:0.08

2:0.07

3:0.06

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

Tube

-1.51

STEP

-1.27

ophon

-1.26

 Tests

-1.26

Def

-1.20

Test

-1.20

 Conservatives

-1.18

itsch

-1.16

iable

-1.14

 Opposition

-1.11

POSITIVE LOGITS

reciation

1.45

�

1.40

�

1.40

lease

1.35

CLS

1.33

)}

1.32

natureconservancy

1.31

 ANGEL

1.29

"}],"

1.28

hell

1.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.