INDEX

Explanations

infinitive forms of verbs indicating desires and intentions

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.11

3:0.09

4:0.06

5:0.02

6:0.08

7:0.15

8:0.03

9:0.04

10:0.14

11:0.20

Negative Logits

ALLY

-1.26

wise

-1.22

ceivable

-1.19

 Whip

-1.18

Favorite

-1.18

Enabled

-1.17

?!

-1.15

pload

-1.14

rn

-1.14

???

-1.13

POSITIVE LOGITS

porary

1.47

iatric

1.39

 unemploy

1.38

iatrics

1.36

 disadvant

1.35

catentry

1.34

 Crate

1.29

 defic

1.28

 glim

1.27

bid

1.27

Activations Density 0.007%

infinitive forms of verbs indicating desires and intentions

No Comments

No Known Activations