INDEX

Explanations

phrases indicating accountability and recommendations related to the governance of First Nations

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.15

1:0.13

2:0.06

3:0.08

4:0.04

5:0.04

6:0.08

7:0.13

8:0.04

9:0.05

10:0.11

11:0.05

Negative Logits

 Cuban

-3.07

 SpaceX

-2.91

 Rubio

-2.89

 Felix

-2.82

 Tesla

-2.79

 Hyundai

-2.79

 Pepe

-2.77

 Drac

-2.70

 Uruguay

-2.68

 Chilean

-2.66

POSITIVE LOGITS

 aboriginal

3.14

owder

2.75

 First

2.73

NF

2.70

NI

2.58

 constitu

2.57

iod

2.56

ipeg

2.55

Nun

2.53

 Laurent

2.53

Activations Density 0.002%

phrases indicating accountability and recommendations related to the governance of First Nations

No Comments

No Known Activations