INDEX

Explanations

phrases related to simulation and its effects

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

2:0.07

3:0.08

4:0.02

5:0.05

6:0.05

7:0.13

8:0.12

9:0.18

10:0.06

11:0.14

Negative Logits

の�

-1.26

 proclaim

-1.22

 rescind

-1.19

 refuses

-1.17

 rightfully

-1.15

 feder

-1.15

 bless

-1.14

liam

-1.13

 forbids

-1.11

 prohibits

-1.10

POSITIVE LOGITS

 scenarios

1.41

 simulation

1.27

 simulations

1.24

effects

1.21

raph

1.20

ゼウス

1.19

Flow

1.18

 simulated

1.18

 scenario

1.14

devices

1.14

Activations Density 0.014%

phrases related to simulation and its effects

No Comments

No Known Activations