INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

1:0.07

2:0.07

3:0.07

4:0.09

5:0.09

6:0.08

7:0.08

8:0.10

9:0.08

10:0.07

11:0.08

Negative Logits

MpServer

-3.15

NetMessage

-2.78

sbm

-2.73

osponsors

-2.58

ebted

-2.57

-2.55

Merit

-2.54

chwitz

-2.54

vir

-2.54

-2.49

POSITIVE LOGITS

 Calder

2.63

Rex

2.42

 Rodrigo

2.37

 Polk

2.35

 spont

2.32

Sea

2.31

 Jefferson

2.29

 ceremonial

2.26

 Fernand

2.26

Pax

2.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.