INDEX

Explanations

references to legal codes and regulations

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.08

1:0.02

2:0.08

3:0.14

4:0.04

5:0.09

6:0.02

7:0.06

8:0.31

9:0.02

10:0.07

11:0.02

Negative Logits

 Elijah

-3.04

bir

-2.79

 Thanksgiving

-2.74

 Manson

-2.74

 Anchorage

-2.73

 Texans

-2.72

 Chevy

-2.65

 Redskins

-2.63

 Jared

-2.61

 Sikh

-2.61

POSITIVE LOGITS

 Luxembourg

4.24

 Directive

3.97

 Netherlands

3.76

 Hague

3.76

MEP

3.75

EU

3.73

 UEFA

3.71

 Article

3.70

 OECD

3.63

 Annex

3.62

Activations Density 0.013%

references to legal codes and regulations

No Comments

No Known Activations