INDEX

Explanations

phrases related to military actions and conflicts

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

words and phrases related to social movements and community activism

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

0:0.06

1:0.06

2:0.15

3:0.24

4:0.02

5:0.03

6:0.09

7:0.08

8:0.05

9:0.05

10:0.07

11:0.05

Negative Logits

eatures

-1.15

 condem

-1.13

 misunder

-1.05

 handcuffs

-1.02

 Rohing

-1.01

Reloaded

-0.98

 cloning

-0.94

 Leopard

-0.94

 Pike

-0.94

 Feld

-0.94

POSITIVE LOGITS

vernment

1.44

 sidx

1.42

asury

1.37

�

1.34

 Marketable

1.29

urrection

1.27

ihad

1.21

vae

1.20

oyal

1.19

ulhu

1.13

Activations Density 0.086%

phrases related to military actions and conflicts

words and phrases related to social movements and community activism

No Comments

No Known Activations