INDEX

Explanations

statements regarding cricket matches and player performances

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.26

1:0.04

2:0.04

3:0.16

4:0.06

5:0.02

6:0.11

7:0.07

8:0.03

9:0.05

10:0.05

11:0.05

Negative Logits

Syrian

-4.02

 Lyft

-3.93

 Bulgar

-3.55

Moscow

-3.49

kaya

-3.47

 Syrians

-3.43

 Elsa

-3.43

 Syrian

-3.39

 Antioch

-3.38

 Idlib

-3.37

POSITIVE LOGITS

 cricket

8.59

 Cricket

8.28

 bowling

6.80

 batting

6.59

 bats

6.55

 Ashes

6.19

Pakistan

6.06

 batted

5.63

 Pakistan

5.52

 innings

5.47

Activations Density 0.141%

statements regarding cricket matches and player performances

No Comments

No Known Activations