INDEX

Explanations

references to eating food

oai_token-act-pair · gpt-3.5-turbo

instances of the word "eat."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

Aus

-0.73

PV

-0.72

 Archangel

-0.71

 McKenna

-0.71

HEL

-0.66

 Constable

-0.66

 Operator

-0.65

 Stellar

-0.65

âĢ¢âĢ¢âĢ¢âĢ¢

-0.64

PBS

-0.64

POSITIVE LOGITS

 eaten

1.01

eat

0.99

 habits

0.97

oleon

0.95

 foods

0.93

eteria

0.92

 meals

0.91

 eating

0.91

ate

0.87

 breakfast

0.87

Activations Density 0.020%

references to eating food

instances of the word "eat."

No Comments

No Known Activations