INDEX

Explanations

historical and biographical information related to individuals named Edward

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

references to historical figures and periods

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

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

0:0.10

1:0.02

2:0.23

3:0.08

4:0.13

5:0.07

6:0.02

7:0.02

8:0.04

9:0.15

10:0.06

11:0.02

Negative Logits

tumblr

-1.47

wcs

-1.45

ULAR

-1.39

imgur

-1.34

IUM

-1.28

itivity

-1.28

Pinterest

-1.26

 intensity

-1.25

cular

-1.21

adium

-1.19

POSITIVE LOGITS

 hatch

1.30

 Morse

1.21

 Wool

1.18

 Tasman

1.18

 Fortune

1.14

ema

1.13

 drone

1.12

 Cust

1.11

 Branch

1.10

 Starg

1.10

Activations Density 0.007%

historical and biographical information related to individuals named Edward

references to historical figures and periods

No Comments

No Known Activations