INDEX

Explanations

phrases indicating quantifiable actions or conditions

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

0:0.09

1:0.03

2:0.08

3:0.07

4:0.06

5:0.08

6:0.06

7:0.06

8:0.29

9:0.05

10:0.04

11:0.04

Negative Logits

 Vienna

-3.87

 Eston

-3.79

loo

-3.28

Georg

-3.16

 Estonia

-3.10

 Czech

-3.06

Aust

-3.04

 Wang

-3.02

 Kabul

-3.00

 Austrian

-2.99

POSITIVE LOGITS

 Apex

4.11

DOJ

4.07

 Bungie

3.92

 Arkham

3.68

 Overwatch

3.64

Justice

3.50

 Metroid

3.48

Agu

3.48

 Inquis

3.46

justice

3.38

Activations Density 0.000%

phrases indicating quantifiable actions or conditions

No Comments

No Known Activations