INDEX

Explanations

references to financial or economic transactions/relationships

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

0:0.04

1:0.02

2:0.06

3:0.04

4:0.05

5:0.04

6:0.30

7:0.04

8:0.06

9:0.23

10:0.02

11:0.05

Negative Logits

Aust

-3.89

ansom

-3.68

Tut

-3.65

 Titus

-3.57

 Cyrus

-3.53

Tat

-3.45

 Sasha

-3.38

 Vienna

-3.37

phony

-3.33

 anat

-3.33

POSITIVE LOGITS

 Green

9.37

Green

9.37

 GREEN

8.87

GREEN

8.54

green

8.04

 Greens

7.22

 green

7.06

 Greene

6.37

 greens

6.30

 Greenpeace

5.99

Activations Density 0.039%

references to financial or economic transactions/relationships

No Comments

No Known Activations