INDEX

Explanations

references to Donald Trump and his political 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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.04

2:0.04

3:0.04

4:0.04

5:0.20

6:0.02

7:0.02

8:0.03

9:0.12

10:0.18

11:0.18

Negative Logits

rals

-1.31

galitarian

-1.29

 Kirin

-1.24

agement

-1.20

onyms

-1.18

agements

-1.16

 capitals

-1.15

rencies

-1.14

Boe

-1.12

ishops

-1.08

POSITIVE LOGITS

needs

1.50

EStreamFrame

1.33

 Himself

1.29

roo

1.26

speed

1.12

 tink

1.12

hower

1.11

him

1.07

 prod

1.07

 sooner

1.07

Activations Density 0.042%

references to Donald Trump and his political activities

No Comments

No Known Activations