INDEX

Explanations

phrases related to incidents of intoxication and public disturbances involving alcohol or drugs

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.07

1:0.02

2:0.13

3:0.23

4:0.03

5:0.18

6:0.02

7:0.09

8:0.07

9:0.01

10:0.08

11:0.02

Negative Logits

cedented

-2.00

 Regulatory

-1.99

 unve

-1.99

 declass

-1.96

 Patent

-1.92

ゼウス

-1.89

 extraord

-1.87

 srfN

-1.85

erning

-1.83

��

-1.83

POSITIVE LOGITS

 pills

2.43

 gunshots

2.34

 girlfriends

2.34

 vodka

2.31

 drugs

2.29

 bananas

2.27

 bruises

2.25

 partying

2.22

 boyfriend

2.21

 sleeping

2.15

Activations Density 0.439%

phrases related to incidents of intoxication and public disturbances involving alcohol or drugs

No Comments

No Known Activations