INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L7_Hcat_z_lr1.20e-03_l11.10e+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.7.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

3:0.09

4:0.06

5:0.06

6:0.09

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

 Deliver

-2.53

 Pigs

-2.46

 Survive

-2.30

Sle

-2.25

 Restoration

-2.23

 Compan

-2.22

 Models

-2.20

 Alive

-2.18

 Tycoon

-2.17

 Simulator

-2.15

POSITIVE LOGITS

uador

2.42

uterte

2.37

luaj

2.35

ichick

2.31

ijing

2.25

ocene

2.20

pecially

2.19

ype

2.19

isite

2.16

okane

2.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.