INDEX

Explanations

phrases that indicate causal relationships, particularly focusing on direct and indirect effects of factors such as age

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.05

1:0.03

2:0.10

3:0.08

4:0.04

5:0.04

6:0.04

7:0.40

8:0.04

9:0.04

10:0.06

11:0.02

Negative Logits

NCT

-2.64

ilee

-2.49

 hardcore

-2.38

 Brittany

-2.31

 bombshell

-2.30

cellence

-2.29

 Bian

-2.27

OTAL

-2.23

inth

-2.22

andals

-2.19

POSITIVE LOGITS

 indirectly

3.75

 indirect

3.63

 intermediary

3.24

 peripher

3.03

 proxies

2.91

 Atmospheric

2.85

illary

2.80

 proxy

2.69

 intermedi

2.68

 secondary

2.67

Activations Density 0.015%

phrases that indicate causal relationships, particularly focusing on direct and indirect effects of factors such as age

No Comments

No Known Activations