INDEX

Explanations

names or references to significant individuals, particularly in politics and military 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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.02

2:0.04

3:0.06

4:0.05

5:0.04

6:0.40

7:0.12

8:0.05

9:0.07

10:0.05

11:0.03

Negative Logits

sylv

-1.37

 crop

-1.36

 daddy

-1.32

 beverage

-1.31

ascript

-1.28

Topics

-1.26

lift

-1.26

 medic

-1.26

 catering

-1.25

stuff

-1.22

POSITIVE LOGITS

��

1.81

henko

1.52

 sqor

1.52

装

1.43

stad

1.36

ansky

1.36

iewicz

1.27

メ

1.26

ンジ

1.24

ynes

1.22

Activations Density 0.003%

names or references to significant individuals, particularly in politics and military contexts

No Comments

No Known Activations