INDEX

Explanations

references to armed entities and violence

oai_token-act-pair · gpt-4o-mini Triggered by @bot

mentions of armed individuals, weaponry, and armed conflicts

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.07

1:0.03

2:0.15

3:0.13

4:0.09

5:0.04

6:0.02

7:0.02

8:0.15

9:0.18

10:0.04

11:0.02

Negative Logits

 Parables

-1.36

 Atlantis

-1.35

 Ratings

-1.31

 Authors

-1.27

TPPStreamerBot

-1.27

isSpecialOrderable

-1.26

 Destination

-1.23

 Lonely

-1.19

 Mathemat

-1.19

ciation

-1.19

POSITIVE LOGITS

 looting

1.32

��

1.30

ppelin

1.27

 paramilitary

1.20

riot

1.18

ooting

1.15

 bombing

1.14

geries

1.14

 motorcycles

1.12

 rifles

1.12

Activations Density 0.021%

references to armed entities and violence

mentions of armed individuals, weaponry, and armed conflicts

No Comments

No Known Activations