INDEX

Explanations

mentions of dishonesty and deceit involving authority figures and legal 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.01

1:0.02

2:0.17

3:0.08

4:0.19

5:0.02

6:0.03

7:0.18

8:0.03

9:0.03

10:0.08

11:0.09

Negative Logits

Interstitial

-1.79

arnaev

-1.69

Coin

-1.61

ディ

-1.52

iggurat

-1.50

irtual

-1.47

enture

-1.47

CONCLUS

-1.46

ISH

-1.43

 largeDownload

-1.40

POSITIVE LOGITS

 uncond

1.55

 Miche

1.40

 grape

1.39

 beforehand

1.30

itably

1.29

 sidelines

1.27

 boundaries

1.26

 omission

1.26

 aloud

1.26

 guarantees

1.26

Activations Density 0.003%

mentions of dishonesty and deceit involving authority figures and legal contexts

No Comments

No Known Activations