INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

2:0.08

3:0.07

4:0.09

5:0.07

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Saul

-1.36

 influences

-1.25

 mentors

-1.24

 Hawking

-1.23

 Alvarez

-1.22

ilateral

-1.22

Mk

-1.21

 Elijah

-1.19

 mechanisms

-1.19

GHC

-1.17

POSITIVE LOGITS

enegger

1.52

UMP

1.45

rien

1.43

 VIDEOS

1.34

ynes

1.33

umblr

1.32

 Instr

1.29

bris

1.28

Veh

1.28

ItemImage

1.27

Activations Density 0.000%

No Known Activations

This feature has no known activations.