INDEX

Explanations

references to a decrease or decline in various contexts

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

phrases that indicate decline or deterioration

oai_token-act-pair · gpt-4o-mini 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

0:0.06

1:0.02

2:0.18

3:0.07

4:0.12

5:0.06

6:0.02

7:0.02

8:0.24

9:0.11

10:0.04

11:0.02

Negative Logits

sand

-1.47

IP

-1.38

BDS

-1.17

clus

-1.14

apest

-1.13

 Bild

-1.11

 RAID

-1.11

 vetoed

-1.10

 commute

-1.10

 Hitch

-1.10

POSITIVE LOGITS

schild

1.55

yth

1.53

BuyableInstoreAndOnline

1.47

��

1.45

aution

1.35

 throats

1.30

 heights

1.28

road

1.26

��

1.24

ecause

1.23

Activations Density 0.008%

references to a decrease or decline in various contexts

phrases that indicate decline or deterioration

No Comments

No Known Activations