INDEX

Explanations

mentions of locations or directions indicating a physical place

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

1:0.02

2:0.15

3:0.07

4:0.21

5:0.09

6:0.03

7:0.02

8:0.06

9:0.16

10:0.05

11:0.03

Negative Logits

��

-1.53

Downloadha

-1.36

leases

-1.35

etheless

-1.35

��

-1.31

etimes

-1.29

��

-1.26

pload

-1.25

enh

-1.23

SN

-1.20

POSITIVE LOGITS

sci

1.51

imester

1.47

thouse

1.39

rimination

1.35

agascar

1.30

#$

1.27

�

1.27

INTON

1.26

inian

1.23

 gasp

1.22

Activations Density 0.007%

mentions of locations or directions indicating a physical place

No Comments

No Known Activations