INDEX

Explanations

references to specific properties and locations associated with Donald Trump

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.24

1:0.03

2:0.03

3:0.07

4:0.11

5:0.04

6:0.14

7:0.10

8:0.02

9:0.08

10:0.03

11:0.07

Negative Logits

 Slayer

-3.77

 Xander

-3.59

adish

-3.29

awa

-3.15

 runners

-2.96

 Boko

-2.95

 Outbreak

-2.93

KP

-2.92

cycl

-2.90

 Cumm

-2.88

POSITIVE LOGITS

 Ivanka

5.57

Trump

5.37

 Trump

5.32

 Kushner

5.31

 TRUMP

5.05

TRUMP

5.04

 Melania

5.02

 Manafort

4.51

afort

4.48

 Bannon

4.41

Activations Density 0.217%

references to specific properties and locations associated with Donald Trump

No Comments

No Known Activations