INDEX

Explanations

mentions of recipes

oai_token-act-pair · gpt-3.5-turbo

references to recipes

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

Not in Any Lists

No Comments

Negative Logits

owers

-0.71

hips

-0.70

oper

-0.68

å¹

-0.67

gc

-0.65

span

-0.64

uty

-0.64

tel

-0.63

asses

-0.63

lands

-0.62

POSITIVE LOGITS

 recipe

3.70

 recipes

2.63

 Recipe

2.53

Recipe

2.19

 Recipes

2.00

 recip

1.66

 ingredient

1.64

reci

1.60

 ingred

1.55

Ingredients

1.54

Activations Density 0.017%

mentions of recipes

references to recipes

No Comments

No Known Activations