INDEX

Explanations

terms associated with measurements and dimensions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.01

2:0.05

3:0.06

4:0.04

5:0.03

6:0.42

7:0.13

8:0.03

9:0.04

10:0.06

11:0.05

Negative Logits

��

-1.78

RIPT

-1.47

isSpecialOrderable

-1.31

forth

-1.21

 istg

-1.18

Tracker

-1.17

 Miko

-1.15

PsyNetMessage

-1.14

ournals

-1.14

 Doomsday

-1.12

POSITIVE LOGITS

atoes

1.47

rouse

1.44

hemy

1.39

lein

1.33

ounters

1.30

hement

1.28

osi

1.27

idge

1.22

ourgeois

1.20

apple

1.20

Activations Density 0.003%

terms associated with measurements and dimensions

No Comments

No Known Activations