INDEX

Explanations

phrases related to discussing or addressing societal issues, policies, and controversies

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

0:0.04

1:0.02

2:0.04

3:0.05

4:0.35

5:0.04

6:0.03

7:0.02

8:0.25

9:0.05

10:0.04

11:0.02

Negative Logits

️

-1.78

acher

-1.42

cius

-1.41

TB

-1.40

 Beetle

-1.38

kie

-1.31

 Chero

-1.29

Wen

-1.28

lander

-1.27

eks

-1.27

POSITIVE LOGITS

 sust

1.83

ateral

1.56

utical

1.54

utics

1.52

 bearer

1.48

ersive

1.42

 resid

1.40

andestine

1.33

adra

1.33

 sanctuary

1.31

Activations Density 0.017%

phrases related to discussing or addressing societal issues, policies, and controversies

No Comments

No Known Activations