INDEX

Explanations

mentions of eating food

oai_token-act-pair · gpt-3.5-turbo

references to eating and food consumption

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

channelAvailability

-0.75

 Lash

-0.70

worthiness

-0.69

 Stellar

-0.68

 Nich

-0.68

 Brist

-0.67

 Jenner

-0.66

 Angola

-0.66

elight

-0.64

 Stra

-0.64

POSITIVE LOGITS

 breakfast

1.07

 meals

1.03

 foods

1.00

 eaten

1.00

 meat

0.97

 scraps

0.97

 nutrit

0.96

 lunch

0.95

 cake

0.95

 food

0.93

Activations Density 0.042%

mentions of eating food

references to eating and food consumption

No Comments

No Known Activations