INDEX

Explanations

person names and locations

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

New Auto-Interp

Top Features by Cosine Similarity

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.05

1:0.04

2:0.19

3:0.06

4:0.20

5:0.08

6:0.04

7:0.03

8:0.05

9:0.14

10:0.05

11:0.03

Negative Logits

DragonMagazine

-1.33

pecially

-1.30

Saharan

-1.29

ケ

-1.29

uggest

-1.28

along

-1.25

BIT

-1.24

 contrace

-1.24

groups

-1.23

���

-1.22

POSITIVE LOGITS

Spa

1.30

Wer

1.24

leen

1.18

riage

1.17

 Warranty

1.14

 improvement

1.14

 Ended

1.12

 Ends

1.11

 Plate

1.09

ufact

1.09

Activations Density 0.004%

person names and locations

No Comments

No Known Activations