INDEX

Explanations

variations of the suffix "-er" in words

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.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

1:0.03

2:0.05

3:0.34

4:0.02

5:0.03

6:0.06

7:0.16

8:0.04

9:0.09

10:0.06

11:0.06

Negative Logits

���

-1.38

PASS

-1.33

BIL

-1.32

IAL

-1.24

++++++++++++++++

-1.23

ו

-1.22

DAY

-1.21

abortion

-1.19

��極

-1.19

ICAN

-1.14

POSITIVE LOGITS

acia

1.36

uador

1.27

 Torrent

1.22

Xu

1.22

atown

1.17

 mosaic

1.16

 suitcase

1.15

 Tycoon

1.14

 Havana

1.12

 Alley

1.12

Activations Density 0.012%

variations of the suffix "-er" in words

No Comments

No Known Activations