INDEX

Explanations

mentions of food specifically referencing beef

oai_token-act-pair · gpt-3.5-turbo

references to beef and related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pmwiki

-0.76

âĸ¬

-0.70

 Stras

-0.65

 Tact

-0.65

guided

-0.64

uyomi

-0.63

 Citizens

-0.63

 Doctrine

-0.62

âĸ¬âĸ¬

-0.61

CPC

-0.60

POSITIVE LOGITS

 beef

1.17

cake

1.15

 Beef

1.03

bean

0.93

meat

0.90

ington

0.90

cakes

0.87

keyes

0.86

alo

0.83

alos

0.83

Activations Density 0.006%

mentions of food specifically referencing beef

references to beef and related contexts

No Comments

No Known Activations