INDEX

Explanations

mentions of actions and consequences related to regulation, safety, and oversight

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

2:0.27

3:0.22

4:0.10

5:0.03

6:0.03

7:0.05

8:0.04

9:0.03

10:0.09

11:0.06

Negative Logits

 Debor

-1.65

 Manit

-1.60

 Adin

-1.56

 Emil

-1.53

 Erica

-1.44

ヴァ

-1.44

 Mesa

-1.43

 Paso

-1.42

 Hosp

-1.40

 Sutherland

-1.40

POSITIVE LOGITS

 slightest

1.67

pires

1.64

 preferably

1.57

oner

1.57

 shalt

1.54

pmwiki

1.48

 anywhere

1.48

 shall

1.45

starter

1.44

 suffice

1.43

Activations Density 0.098%

mentions of actions and consequences related to regulation, safety, and oversight

No Comments

No Known Activations