INDEX

Explanations

terms and concepts related to particle physics and particle detectors

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

terms related to particle physics and their properties

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att-kk

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

Head Attr Weights

0:0.01

1:0.03

2:0.07

3:0.15

4:0.04

5:0.05

6:0.14

7:0.23

8:0.04

9:0.04

10:0.06

11:0.08

Negative Logits

 Macy

-1.32

interstitial

-1.27

holiday

-1.25

 rumors

-1.19

 Pavilion

-1.18

Kids

-1.16

 Chocobo

-1.13

 Discount

-1.12

stown

-1.09

 celebrations

-1.07

POSITIVE LOGITS

 atoms

1.38

 orbit

1.28

axis

1.23

 irrad

1.22

etsk

1.20

 oxid

1.20

 oxide

1.20

istor

1.19

 membranes

1.18

RNA

1.17

Activations Density 0.021%

terms and concepts related to particle physics and particle detectors

terms related to particle physics and their properties

No Known Activations