INDEX

Explanations

phrases related to decision-making and personal responsibility

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.03

2:0.14

3:0.08

4:0.16

5:0.05

6:0.02

7:0.02

8:0.21

9:0.11

10:0.04

11:0.02

Negative Logits

hovah

-1.49

aughed

-1.46

opoulos

-1.41

eele

-1.33

ifted

-1.32

phrine

-1.32

ogun

-1.32

angering

-1.31

 traged

-1.30

gio

-1.27

POSITIVE LOGITS

ドラゴン

1.36

Lay

1.34

き

1.33

Unique

1.27

 nests

1.25

 niche

1.24

版

1.24

 Ital

1.23

Region

1.23

-+-+

1.19

Activations Density 0.003%

phrases related to decision-making and personal responsibility

No Comments

No Known Activations