INDEX

Explanations

elements related to discussions or transactions in sports

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

0:0.21

1:0.08

2:0.07

3:0.04

4:0.03

5:0.03

6:0.10

7:0.16

8:0.03

9:0.03

10:0.13

11:0.03

Negative Logits

ETF

-2.73

 Thiel

-2.65

 Ottoman

-2.60

Esk

-2.56

Nun

-2.56

 Unic

-2.53

clo

-2.50

 Rapt

-2.48

Dre

-2.46

 Waterloo

-2.45

POSITIVE LOGITS

 Martinez

7.89

Mart

5.33

inez

5.12

 Gomez

4.07

 Ramirez

4.04

 Mart

3.99

 Pedro

3.64

 Ramos

3.60

 Ortiz

3.47

mart

3.45

Activations Density 0.004%

elements related to discussions or transactions in sports

No Comments

No Known Activations