INDEX

Explanations

references to player positions and roles in a sports context, particularly in football

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

0:0.03

1:0.02

2:0.04

3:0.05

4:0.05

5:0.04

6:0.04

7:0.03

8:0.03

9:0.06

10:0.43

11:0.13

Negative Logits

 embargo

-1.52

 crem

-1.44

 apocalyptic

-1.44

 regret

-1.42

 ferment

-1.40

iversary

-1.39

 decree

-1.39

cens

-1.37

 guilt

-1.36

 regrets

-1.36

POSITIVE LOGITS

Position

1.70

 Fowler

1.63

role

1.62

 Serge

1.58

Buff

1.49

 Boise

1.49

 Norris

1.49

 Assist

1.49

 Sutton

1.48

tackle

1.48

Activations Density 0.357%

references to player positions and roles in a sports context, particularly in football

No Comments

No Known Activations