INDEX

Explanations

expressions indicating approximate time or location

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

0:0.02

1:0.01

2:0.05

3:0.08

4:0.10

5:0.04

6:0.22

7:0.04

8:0.04

9:0.03

10:0.07

11:0.24

Negative Logits

 flashbacks

-1.46

 worse

-1.44

 scarce

-1.36

 Outlook

-1.34

gencies

-1.31

 Boone

-1.29

 denote

-1.28

 sooner

-1.26

 regrets

-1.26

 wors

-1.24

POSITIVE LOGITS

ffen

1.68

audi

1.61

heid

1.61

ngth

1.59

engine

1.56

fen

1.55

neutral

1.52

competitive

1.49

obin

1.46

ettel

1.46

Activations Density 0.001%

expressions indicating approximate time or location

No Comments

No Known Activations