INDEX

Explanations

the appearance of the name "Mark" in the text

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.09

1:0.08

2:0.09

3:0.11

4:0.08

5:0.06

6:0.07

7:0.08

8:0.06

9:0.08

10:0.09

11:0.06

Negative Logits

 Bucs

-3.69

 Georgia

-3.68

Georgia

-3.60

 Florida

-3.49

Florida

-3.32

 Tennessee

-3.31

 Buccaneers

-3.16

 Alabama

-3.05

Gw

-2.91

 Tampa

-2.88

POSITIVE LOGITS

krit

2.75

 Hebdo

2.62

inventoryQuantity

2.50

 Remy

2.43

 ration

2.41

uj

2.34

 kosher

2.31

 partName

2.31

 intrins

2.30

jit

2.28

Activations Density 0.000%

the appearance of the name "Mark" in the text

No Comments

No Known Activations