INDEX

Explanations

occurrences related to racing and competition metrics

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.03

2:0.08

3:0.04

4:0.04

5:0.05

6:0.38

7:0.03

8:0.06

9:0.14

10:0.02

11:0.02

Negative Logits

 lettuce

-4.04

 Keller

-3.58

 Ballard

-3.56

 Heal

-3.46

 Baxter

-3.45

 Bent

-3.42

 Beckham

-3.34

Ot

-3.32

 Coil

-3.30

hern

-3.29

POSITIVE LOGITS

 Race

9.60

Race

9.08

 race

8.68

 races

8.18

race

8.11

 Races

7.74

 racer

6.88

 racing

6.80

Rac

6.73

 raced

6.25

Activations Density 0.032%

occurrences related to racing and competition metrics

No Comments

No Known Activations