INDEX

Explanations

phrases related to family relationships and legal matters

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.04

1:0.02

2:0.18

3:0.05

4:0.31

5:0.05

6:0.02

7:0.02

8:0.05

9:0.14

10:0.04

11:0.02

Negative Logits

obal

-1.47

thal

-1.45

oby

-1.37

wcs

-1.31

swe

-1.31

qual

-1.30

ocl

-1.30

yp

-1.26

stat

-1.26

�

-1.26

POSITIVE LOGITS

 attendants

1.43

 leukemia

1.40

 experien

1.36

 traged

1.36

 Frankenstein

1.34

 sclerosis

1.33

 elders

1.33

aukee

1.32

 anecdotes

1.32

 physicians

1.32

Activations Density 0.019%

phrases related to family relationships and legal matters

No Comments

No Known Activations