INDEX

Explanations

references to religious affiliations and sectarian identities

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.02

1:0.02

2:0.06

3:0.06

4:0.04

5:0.04

6:0.29

7:0.06

8:0.04

9:0.06

10:0.18

11:0.06

Negative Logits

��

-1.73

 Prometheus

-1.56

pmwiki

-1.54

assetsadobe

-1.53

ovember

-1.52

 Lilly

-1.48

channelAvailability

-1.48

 horm

-1.45

ILLE

-1.41

 Collider

-1.41

POSITIVE LOGITS

tsky

1.78

 separatists

1.57

ahu

1.49

astern

1.47

orsi

1.44

 dominated

1.44

 dominates

1.43

 separatist

1.43

ipal

1.42

 nationalist

1.40

Activations Density 0.001%

references to religious affiliations and sectarian identities

No Comments

No Known Activations