INDEX

Explanations

references to policies and decision-making processes

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_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

0:0.06

1:0.03

2:0.06

3:0.06

4:0.08

5:0.06

6:0.03

7:0.03

8:0.37

9:0.07

10:0.06

11:0.03

Negative Logits

 tackled

-1.52

 flung

-1.41

 swapped

-1.37

 repaired

-1.32

 honoured

-1.31

 vetoed

-1.30

 punished

-1.30

 accounted

-1.28

 impacted

-1.28

 ushered

-1.27

POSITIVE LOGITS

 Paleo

1.36

 proprietary

1.36

ULAR

1.35

advertisement

1.34

 presupp

1.31

hz

1.29

 Patreon

1.29

orically

1.27

 Saying

1.21

 Religion

1.19

Activations Density 0.005%

references to policies and decision-making processes

No Comments

No Known Activations