INDEX

Explanations

references to corporate policies and legal matters

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

0:0.23

1:0.02

2:0.10

3:0.05

4:0.04

5:0.07

6:0.11

7:0.05

8:0.06

9:0.15

10:0.03

11:0.04

Negative Logits

natureconservancy

-3.44

~~~~~~~~

-3.38

ilers

-2.90

Training

-2.78

 shadows

-2.76

 irrad

-2.74

Strength

-2.71

irlwind

-2.70

 Guardiola

-2.68

 blinding

-2.65

POSITIVE LOGITS

 eBay

8.52

 Etsy

6.05

 PayPal

5.93

 Seller

5.24

 Craigslist

5.05

 Auction

4.96

 auctions

4.95

 seller

4.90

 sellers

4.78

 auction

4.53

Activations Density 0.007%

references to corporate policies and legal matters

No Comments

No Known Activations