INDEX

Explanations

phrases indicating values and taxes related to economic discussions

oai_token-act-pair · gpt-4o-mini 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

0:0.05

1:0.02

2:0.20

3:0.03

4:0.27

5:0.05

6:0.02

7:0.03

8:0.05

9:0.18

10:0.04

11:0.02

Negative Logits

istar

-1.48

Haf

-1.39

thia

-1.33

scrib

-1.32

Nusra

-1.30

Ruk

-1.30

asio

-1.27

rea

-1.27

ften

-1.25

wcs

-1.24

POSITIVE LOGITS

 extraction

1.49

 immersion

1.47

 compression

1.43

 investments

1.43

 assets

1.41

 investment

1.40

 gamble

1.36

 parity

1.34

(%

1.33

 percentile

1.31

Activations Density 0.012%

phrases indicating values and taxes related to economic discussions

No Comments

No Known Activations