INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.06

1:0.06

2:0.09

3:0.09

4:0.08

5:0.08

6:0.07

7:0.07

8:0.09

9:0.07

10:0.09

11:0.09

Negative Logits

querade

-1.50

XT

-1.41

 lined

-1.32

 taxis

-1.30

 Masquerade

-1.30

 sleek

-1.29

ezvous

-1.27

 surn

-1.21

 Mirage

-1.20

 Schne

-1.19

POSITIVE LOGITS

=-=-=-=-

1.65

inem

1.65

ensable

1.64

 istg

1.52

ONSORED

1.50

ategic

1.43

poses

1.38

partisan

1.37

 helps

1.36

 mins

1.34

Activations Density 0.000%

No Known Activations

This feature has no known activations.