INDEX

Explanations

actions related to carrying out attacks or operations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.05

1:0.01

2:0.12

3:0.05

4:0.12

5:0.03

6:0.23

7:0.05

8:0.04

9:0.05

10:0.08

11:0.13

Negative Logits

hao

-1.42

 workforce

-1.37

 pregn

-1.32

doc

-1.30

 hust

-1.30

 uncond

-1.25

 volunt

-1.22

 rollout

-1.22

 reckoning

-1.19

 opio

-1.19

POSITIVE LOGITS

actionDate

1.72

eph

1.48

idan

1.45

related

1.34

sea

1.31

�

1.26

stones

1.26

uts

1.26

 Nanto

1.25

�

1.24

Activations Density 0.007%

actions related to carrying out attacks or operations

No Comments

No Known Activations