INDEX

Explanations

references to political parties and their candidates

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

1:0.01

2:0.05

3:0.05

4:0.08

5:0.03

6:0.31

7:0.15

8:0.02

9:0.04

10:0.11

11:0.06

Negative Logits

 varied

-1.33

lux

-1.22

 snug

-1.21

 Wonderland

-1.19

 tailored

-1.18

 Provided

-1.17

 pets

-1.17

 Remastered

-1.16

 parcel

-1.16

 narrower

-1.15

POSITIVE LOGITS

SpaceEngineers

1.35

�

1.33

agonist

1.28

llor

1.26

avan

1.25

unic

1.24

 Alam

1.23

endment

1.22

Cla

1.22

ENA

1.20

Activations Density 0.000%

references to political parties and their candidates

No Comments

No Known Activations