INDEX

Explanations

proper nouns, specifically focusing on locations or names

oai_token-act-pair · gpt-3.5-turbo

the name "Kun" and its various mentions in the context of military or strategic operations

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 tolerant

-0.71

prop

-0.67

 acceptance

-0.65

 cath

-0.63

 prep

-0.63

rss

-0.63

 olive

-0.63

expr

-0.58

 adoption

-0.58

 marg

-0.57

POSITIVE LOGITS

Kun

4.19

Yun

1.43

Tsu

1.34

 Kund

1.33

Kut

1.31

Kur

1.25

 Kand

1.21

kun

1.20

Kub

1.20

 Kahn

1.17

Activations Density 0.013%

proper nouns, specifically focusing on locations or names

the name "Kun" and its various mentions in the context of military or strategic operations

No Known Activations