INDEX

Explanations

references to investigations and reports related to health authorities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.16

1:0.03

2:0.15

3:0.07

4:0.04

5:0.06

6:0.05

7:0.05

8:0.22

9:0.06

10:0.04

11:0.02

Negative Logits

 foreclosure

-3.74

 Klan

-3.23

bleacher

-3.20

Kings

-3.18

riots

-3.17

 Sheriff

-3.08

bernatorial

-3.08

 Fargo

-3.06

paio

-3.04

 rentals

-3.02

POSITIVE LOGITS

WHO

6.65

WHO

5.21

 Ebola

4.09

 OECD

4.03

 UNHCR

3.91

 Nigeria

3.81

 malaria

3.69

 Geneva

3.67

 epidem

3.62

 Lancet

3.61

Activations Density 0.010%

references to investigations and reports related to health authorities

No Comments

No Known Activations