INDEX

Explanations

phrases indicating the passage of time and calls to action

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_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

0:0.01

1:0.02

2:0.07

3:0.11

4:0.08

5:0.02

6:0.07

7:0.38

8:0.02

9:0.03

10:0.05

11:0.08

Negative Logits

redited

-1.44

 errone

-1.35

aneous

-1.35

 PsyNet

-1.31

 gist

-1.29

 False

-1.27

 incorrectly

-1.26

 cited

-1.24

atial

-1.22

 grants

-1.21

POSITIVE LOGITS

wcs

1.75

inement

1.73

 retire

1.52

eters

1.52

grave

1.52

accompan

1.50

NOW

1.50

 reckoning

1.49

 reconsider

1.47

ffen

1.45

Activations Density 0.014%

phrases indicating the passage of time and calls to action

No Comments

No Known Activations