INDEX

Explanations

prepositions and their accompanying nouns or phrases

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

New Auto-Interp

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

0:0.01

1:0.01

2:0.05

3:0.04

4:0.12

5:0.02

6:0.48

7:0.09

8:0.02

9:0.03

10:0.03

11:0.04

Negative Logits

bourg

-1.44

igmat

-1.42

装

-1.31

 Borg

-1.31

ucci

-1.28

umbnails

-1.27

PDATE

-1.27

aiden

-1.24

 Cham

-1.23

ット

-1.18

POSITIVE LOGITS

��

1.30

aroo

1.30

 skirts

1.27

TOD

1.26

 seams

1.24

 stairs

1.22

course

1.21

govtrack

1.18

sed

1.18

atche

1.17

Activations Density 0.082%

prepositions and their accompanying nouns or phrases

No Comments

No Known Activations