INDEX

Explanations

content related to numerical ratings and reviews

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.02

1:0.01

2:0.17

3:0.10

4:0.11

5:0.04

6:0.06

7:0.17

8:0.03

9:0.05

10:0.10

11:0.08

Negative Logits

sic

-1.51

 semblance

-1.34

Oss

-1.32

 Rove

-1.30

 vanished

-1.25

 Flowers

-1.22

 pupils

-1.22

 roots

-1.20

 Overt

-1.20

 handshake

-1.19

POSITIVE LOGITS

assetsadobe

1.91

fml

1.73

cedented

1.60

taboola

1.59

ヴァ

1.57

abyte

1.49

cipled

1.46

�

1.45

ventory

1.43

ヤ

1.42

Activations Density 0.001%

content related to numerical ratings and reviews

No Comments

No Known Activations