INDEX

Explanations

terms related to legal or medical contexts, particularly involving defendants, plaintiffs, employers, employees, and medical considerations

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

0:0.37

1:0.02

2:0.04

3:0.03

4:0.10

5:0.07

6:0.09

7:0.05

8:0.03

9:0.03

10:0.09

11:0.03

Negative Logits

VIDIA

-1.45

hement

-1.37

 Flavoring

-1.35

ypes

-1.34

aughtered

-1.32

ulously

-1.30

htaking

-1.23

nces

-1.22

acebook

-1.22

POSITIVE LOGITS

 Owner

1.28

erk

1.28

ocent

1.24

ATURE

1.23

Vor

1.22

 Partner

1.21

 receiving

1.21

 residence

1.20

 Submit

1.19

 possessions

1.17

Activations Density 0.214%

terms related to legal or medical contexts, particularly involving defendants, plaintiffs, employers, employees, and medical considerations

No Comments

No Known Activations