INDEX

Explanations

elements related to personal or private information and digital communication

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

0:0.05

1:0.08

2:0.04

3:0.07

4:0.05

5:0.03

6:0.05

7:0.08

8:0.04

9:0.08

10:0.05

11:0.34

Negative Logits

 layers

-2.95

 formations

-2.83

 elements

-2.65

 varieties

-2.49

 pillars

-2.44

 types

-2.39

types

-2.37

 facets

-2.27

 Element

-2.27

 layer

-2.26

POSITIVE LOGITS

 homes

2.73

HOME

2.59

home

2.56

Home

2.53

 homepage

2.53

ebin

2.41

paio

2.41

 HOME

2.32

 home

2.29

wallet

2.27

Activations Density 0.010%

elements related to personal or private information and digital communication

No Comments

No Known Activations