INDEX

Explanations

specific model names and technical details related to vehicles, especially in the context of racing

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

references to specific car models and racing context

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-att-kk

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.06

1:0.04

2:0.24

3:0.07

4:0.16

5:0.08

6:0.02

7:0.03

8:0.05

9:0.12

10:0.06

11:0.02

Negative Logits

 Peoples

-1.24

jan

-1.24

 prayer

-1.23

 particip

-1.17

 miscar

-1.14

 bapt

-1.13

 Occupy

-1.10

NPR

-1.10

 dormant

-1.08

 Tent

-1.08

POSITIVE LOGITS

FIG

1.45

endish

1.44

ioxide

1.41

INESS

1.38

ngth

1.35

️

1.30

agall

1.30

 Fenrir

1.29

chnology

1.28

olester

1.27

Activations Density 0.005%

specific model names and technical details related to vehicles, especially in the context of racing

references to specific car models and racing context

No Comments

No Known Activations