INDEX

Explanations

phrases related to manufacturing processes and factory operations

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

phrases related to factory production and issues surrounding it

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

0:0.05

1:0.04

2:0.18

3:0.05

4:0.06

5:0.08

6:0.04

7:0.05

8:0.05

9:0.25

10:0.07

11:0.03

Negative Logits

 contagious

-1.38

aucas

-1.32

ander

-1.22

ּ

-1.20

abus

-1.19

 psychiat

-1.18

etrical

-1.17

stro

-1.17

 eclipse

-1.16

abis

-1.16

POSITIVE LOGITS

 warehouses

1.38

hesion

1.37

enment

1.25

 srfAttach

1.18

osures

1.17

closed

1.16

 Inspection

1.14

Eff

1.14

ngth

1.13

 Worker

1.13

Activations Density 0.020%

phrases related to manufacturing processes and factory operations

phrases related to factory production and issues surrounding it

No Comments

No Known Activations