INDEX

Explanations

references to geographical locations and entities involved in medical or governmental 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.12

1:0.03

2:0.09

3:0.08

4:0.03

5:0.06

6:0.04

7:0.06

8:0.33

9:0.04

10:0.03

11:0.03

Negative Logits

Toronto

-4.44

icago

-3.52

 Milwaukee

-3.51

 Raptors

-3.44

waukee

-3.29

 Toronto

-3.24

Detroit

-3.07

York

-3.06

TTC

-3.05

Philadelphia

-3.00

POSITIVE LOGITS

 Liberia

6.46

 Guinea

5.47

 Ebola

4.63

 Sierra

3.98

 Cameroon

3.94

 Angola

3.86

 Liber

3.81

 malaria

3.67

 Leone

3.45

 Senegal

3.38

Activations Density 0.003%

references to geographical locations and entities involved in medical or governmental contexts

No Comments

No Known Activations