INDEX

Explanations

references to decision-making processes, particularly in cooperative contexts or game theory scenarios

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.08

1:0.04

2:0.09

3:0.26

4:0.04

5:0.12

6:0.04

7:0.08

8:0.02

9:0.04

10:0.10

11:0.03

Negative Logits

 churches

-2.73

 colleges

-2.56

 universities

-2.54

 studios

-2.50

 laboratories

-2.49

 Churches

-2.42

 dictators

-2.41

 Universities

-2.37

 campuses

-2.34

 sects

-2.29

POSITIVE LOGITS

 clicked

2.19

Previous

2.19

ancel

2.18

 incoming

2.15

 downed

2.14

 item

2.14

sent

2.13

 requested

2.13

Done

2.12

Result

2.10

Activations Density 0.597%

references to decision-making processes, particularly in cooperative contexts or game theory scenarios

No Comments

No Known Activations