INDEX

Explanations

words indicating geographical directions

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

0:0.15

1:0.02

2:0.13

3:0.04

4:0.09

5:0.04

6:0.11

7:0.03

8:0.13

9:0.04

10:0.05

11:0.12

Negative Logits

 Conversion

-1.54

MJ

-1.48

anca

-1.43

NON

-1.28

 planner

-1.27

��

-1.25

 Spread

-1.21

 Intelligent

-1.21

icion

-1.20

icides

-1.18

POSITIVE LOGITS

 corners

1.59

)=(

1.48

hedon

1.37

 recess

1.37

 vents

1.35

ember

1.35

 coasts

1.31

 depending

1.30

hess

1.30

�

1.27

Activations Density 0.006%

words indicating geographical directions

No Comments

No Known Activations