INDEX

Explanations

comparative phrases indicating superiority or preference

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

1:0.00

2:0.11

3:0.06

4:0.09

5:0.02

6:0.21

7:0.28

8:0.04

9:0.02

10:0.03

11:0.06

Negative Logits

ickr

-1.65

oday

-1.55

wick

-1.39

ocry

-1.36

ecd

-1.36

iday

-1.33

oscope

-1.32

archive

-1.29

 slang

-1.28

edin

-1.28

POSITIVE LOGITS

ocious

1.62

DonaldTrump

1.40

psey

1.38

Charges

1.33

RANT

1.32

 Kemp

1.30

 Loki

1.30

OPA

1.28

kus

1.27

RAG

1.26

Activations Density 0.000%

comparative phrases indicating superiority or preference

No Comments

No Known Activations