INDEX

Explanations

instances of the letter "o" in various contexts

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

0:0.02

1:0.01

2:0.05

3:0.04

4:0.04

5:0.03

6:0.37

7:0.11

8:0.04

9:0.06

10:0.13

11:0.05

Negative Logits

 GOODMAN

-1.42

minecraft

-1.35

ecause

-1.29

eworks

-1.29

 coincidence

-1.28

 Comcast

-1.27

ccoli

-1.27

asions

-1.24

 curl

-1.23

�

-1.22

POSITIVE LOGITS

 Expend

1.39

ikuman

1.33

omore

1.32

戦

1.29

RAW

1.28

ommel

1.23

civil

1.21

EStream

1.21

elta

1.21

 Mastery

1.20

Activations Density 0.001%

instances of the letter "o" in various contexts

No Comments

No Known Activations