INDEX

Explanations

country names and their associations, particularly in political contexts

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

0:0.07

1:0.03

2:0.06

3:0.07

4:0.04

5:0.07

6:0.04

7:0.05

8:0.41

9:0.03

10:0.04

11:0.04

Negative Logits

 NYPD

-3.07

 Chinatown

-2.77

 Liang

-2.75

 Ahmad

-2.71

Shi

-2.70

asury

-2.69

MSG

-2.66

 Nass

-2.66

 Kahn

-2.65

Lau

-2.61

POSITIVE LOGITS

Brazil

3.94

 Peru

3.71

 Paragu

3.56

Dutch

3.16

 Brazil

3.11

 Liberia

3.06

 Lima

3.03

 Colombia

3.02

 Argentina

3.01

 Congo

2.92

Activations Density 0.001%

country names and their associations, particularly in political contexts

No Comments

No Known Activations