INDEX

Explanations

instances of the word "to" and its usage 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

0:0.01

1:0.01

2:0.12

3:0.06

4:0.09

5:0.03

6:0.03

7:0.20

8:0.05

9:0.03

10:0.08

11:0.23

Negative Logits

��

-1.79

icum

-1.58

ワ

-1.54

��

-1.47

���

-1.46

 サーティワン

-1.41

STEM

-1.41

weed

-1.40

の�

-1.38

corn

-1.36

POSITIVE LOGITS

Lol

1.49

 incorpor

1.37

ega

1.37

authent

1.35

 altogether

1.32

irlf

1.30

cas

1.29

MX

1.28

az

1.28

 Coco

1.28

Activations Density 0.010%

instances of the word "to" and its usage in various contexts

No Comments

No Known Activations