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

4:0.08

5:0.09

6:0.08

7:0.08

8:0.07

9:0.06

10:0.08

11:0.09

Negative Logits

)</

-1.47

Parts

-1.27

 tradem

-1.22

 rehe

-1.20

catentry

-1.20

quartered

-1.17

HAEL

-1.16

 flats

-1.14

 percussion

-1.13

 pickups

-1.13

POSITIVE LOGITS

 unworthy

1.42

albeit

1.39

spir

1.30

�

1.28

efe

1.26

*:

1.24

lude

1.22

icious

1.21

USER

1.21

ealous

1.20

Activations Density 0.000%

No Known Activations

This feature has no known activations.