INDEX

Explanations

references to leadership and authoritative figures

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

0:0.06

1:0.10

2:0.04

3:0.06

4:0.05

5:0.02

6:0.27

7:0.13

8:0.02

9:0.05

10:0.04

11:0.10

Negative Logits

 Asylum

-2.77

 Cosby

-2.60

 Mechdragon

-2.55

 Purchase

-2.47

 sued

-2.41

 Berman

-2.40

Purchase

-2.34

��極

-2.33

checks

-2.33

 Lovecraft

-2.32

POSITIVE LOGITS

 leader

6.13

 leadership

5.96

 leaders

5.74

 Leader

5.50

 Leaders

5.44

Leader

5.22

leader

5.12

leaders

5.10

 Leadership

4.88

Lead

4.21

Activations Density 0.093%

references to leadership and authoritative figures

No Comments

No Known Activations