INDEX

Explanations

text related to movements and actions involving driving or being driven somewhere

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

references to movement or travel

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.03

2:0.13

3:0.06

4:0.10

5:0.09

6:0.03

7:0.02

8:0.20

9:0.11

10:0.06

11:0.03

Negative Logits

krit

-1.46

olars

-1.46

asury

-1.41

nces

-1.34

pson

-1.29

yip

-1.28

ept

-1.25

FORE

-1.24

thora

-1.24

gemony

-1.23

POSITIVE LOGITS

 pedestrians

1.36

 interstate

1.36

 injuring

1.26

 BART

1.26

 upright

1.25

 wedge

1.23

 opposite

1.23

 brakes

1.22

 treadmill

1.22

 freeway

1.19

Activations Density 0.009%

text related to movements and actions involving driving or being driven somewhere

references to movement or travel

No Comments

No Known Activations