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

0:0.10

1:0.08

2:0.09

3:0.08

4:0.07

5:0.08

6:0.08

7:0.06

8:0.07

9:0.07

10:0.08

11:0.08

Negative Logits

CLASSIFIED

-1.57

Ire

-1.44

ウス

-1.39

 epile

-1.38

enment

-1.37

 asylum

-1.37

ギ

-1.30

 coli

-1.30

ENTS

-1.26

ガ

-1.23

POSITIVE LOGITS

umenthal

1.53

 succeed

1.39

wcsstore

1.36

theless

1.31

 alike

1.30

 Netanyahu

1.28

 Tillerson

1.27

 Pinterest

1.26

 Cosponsors

1.25

ractical

1.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.