INDEX

Explanations

phrases that express commands or requests to stop, particularly in a confrontational context

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

2:0.06

3:0.06

4:0.20

5:0.05

6:0.09

7:0.29

8:0.04

9:0.04

10:0.05

11:0.04

Negative Logits

覚醒

-2.15

enegger

-1.59

QL

-1.57

merce

-1.51

 Parables

-1.42

ModLoader

-1.41

cair

-1.40

cham

-1.38

ixel

-1.38

��

-1.38

POSITIVE LOGITS

 leash

1.89

lid

1.78

 doors

1.77

 door

1.75

 reins

1.71

 drawer

1.69

 brakes

1.66

 accountable

1.65

 Doors

1.56

eye

1.54

Activations Density 0.002%

phrases that express commands or requests to stop, particularly in a confrontational context

No Comments

No Known Activations