INDEX

Explanations

instances of signing documents or agreements

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

2:0.04

3:0.04

4:0.18

5:0.02

6:0.06

7:0.41

8:0.02

9:0.02

10:0.08

11:0.06

Negative Logits

icult

-1.71

 distractions

-1.41

xual

-1.39

uncture

-1.38

CVE

-1.37

SPONSORED

-1.37

GROUND

-1.35

Discuss

-1.34

 harass

-1.34

asive

-1.34

POSITIVE LOGITS

 pact

2.04

 Signed

1.78

 contracts

1.77

 Agreement

1.76

 agreements

1.74

 waiver

1.69

 Declaration

1.68

 agreement

1.67

 covenant

1.63

signed

1.61

Activations Density 0.023%

instances of signing documents or agreements

No Comments

No Known Activations