INDEX

Explanations

references to corporate headquarters and their locations

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_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

0:0.03

1:0.02

2:0.09

3:0.04

4:0.06

5:0.04

6:0.06

7:0.14

8:0.04

9:0.04

10:0.28

11:0.11

Negative Logits

iasis

-1.46

 crochet

-1.44

 remedies

-1.39

 diets

-1.35

 harsher

-1.24

acial

-1.23

 Rican

-1.23

Adds

-1.19

 allele

-1.19

 punishments

-1.19

POSITIVE LOGITS

 Headquarters

1.62

 headquarters

1.51

AFB

1.49

 Canaveral

1.38

display

1.36

 occupied

1.35

 occupant

1.33

staff

1.32

occupied

1.30

 Booth

1.29

Activations Density 0.004%

references to corporate headquarters and their locations

No Comments

No Known Activations