INDEX

Explanations

numerical values or statistics described in text

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.01

2:0.24

3:0.07

4:0.34

5:0.04

6:0.02

7:0.01

8:0.05

9:0.07

10:0.03

11:0.01

Negative Logits

sworth

-1.56

worth

-1.41

bery

-1.38

steen

-1.38

gow

-1.37

 fulfillment

-1.37

sterdam

-1.35

 Thornton

-1.30

 philos

-1.28

dur

-1.28

POSITIVE LOGITS

incial

1.61

xual

1.56

IVE

1.56

roups

1.54

isans

1.52

 Flavoring

1.47

Region

1.45

Saharan

1.45

ascript

1.42

�

1.42

Activations Density 0.015%

numerical values or statistics described in text

No Comments

No Known Activations