INDEX

Explanations

the word "of" in various contexts

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

0:0.03

1:0.02

2:0.07

3:0.05

4:0.06

5:0.03

6:0.25

7:0.21

8:0.04

9:0.04

10:0.07

11:0.09

Negative Logits

ENE

-1.65

Sort

-1.48

 Antar

-1.48

 Alone

-1.39

competitive

-1.37

Bonus

-1.35

 Nightmare

-1.34

 Solo

-1.30

cru

-1.27

insk

-1.23

POSITIVE LOGITS

lain

1.64

 publications

1.60

 writings

1.42

 literature

1.42

 acknowledgement

1.40

 papers

1.40

SHA

1.37

 declarations

1.30

 encour

1.27

alions

1.27

Activations Density 0.001%

the word "of" in various contexts

No Comments

No Known Activations