INDEX

Explanations

phrases indicating moral or ethical considerations

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

1:0.02

2:0.10

3:0.05

4:0.05

5:0.02

6:0.25

7:0.29

8:0.03

9:0.03

10:0.06

11:0.05

Negative Logits

imentary

-1.92

覚醒

-1.70

 Daly

-1.40

 Weeks

-1.40

龍契士

-1.40

̶

-1.37

lees

-1.37

Grab

-1.36

chieve

-1.29

 enthusi

-1.28

POSITIVE LOGITS

theme

1.52

ismo

1.45

ipolar

1.38

orthodox

1.38

geist

1.38

cc

1.37

late

1.35

 opin

1.33

 reborn

1.33

amiliar

1.31

Activations Density 0.004%

phrases indicating moral or ethical considerations

No Comments

No Known Activations