INDEX

Explanations

references to political parties and their activities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.03

2:0.07

3:0.10

4:0.06

5:0.08

6:0.04

7:0.03

8:0.04

9:0.13

10:0.20

11:0.13

Negative Logits

anski

-1.27

 Ogre

-1.25

gaard

-1.17

 Krug

-1.16

 Javascript

-1.14

zsche

-1.11

 WordPress

-1.11

osaurus

-1.10

SOM

-1.10

 nested

-1.08

POSITIVE LOGITS

 Himself

1.29

■

1.28

nesty

1.26

�

1.24

 rallies

1.21

 charity

1.15

 independents

1.13

iliation

1.11

gement

1.10

 Leader

1.10

Activations Density 0.173%

references to political parties and their activities

No Comments

No Known Activations