INDEX

Explanations

mentions of temporary or quickly organized structures and facilities

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

references to temporary or improvised structures or items

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

0:0.03

1:0.03

2:0.08

3:0.08

4:0.02

5:0.05

6:0.11

7:0.15

8:0.06

9:0.03

10:0.08

11:0.22

Negative Logits

ahime

-1.59

hematically

-1.27

cially

-1.25

cipled

-1.22

ophical

-1.20

eeper

-1.17

olutely

-1.16

audi

-1.11

azeera

-1.10

ovies

-1.09

POSITIVE LOGITS

 makeshift

1.24

 chore

1.19

 improvised

1.16

 corrid

1.13

 greeting

1.08

styles

1.04

 salv

1.02

script

1.01

 resembling

0.99

thank

0.97

Activations Density 0.020%

mentions of temporary or quickly organized structures and facilities

references to temporary or improvised structures or items

No Comments

No Known Activations