INDEX

Explanations

phrases related to food and nutrition

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

Data Type

torch.float32

Hook Point

blocks.8.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

 Caldwell

-0.74

worthiness

-0.74

Jed

-0.72

âĢ¢âĢ¢âĢ¢âĢ¢

-0.68

 Trooper

-0.67

 Powers

-0.66

 Gemini

-0.65

 Armory

-0.65

 Archangel

-0.64

channelAvailability

-0.63

POSITIVE LOGITS

eteria

1.11

 meals

1.11

 eaten

1.10

bowl

1.00

 breakfast

0.98

 eater

0.98

mone

0.97

 meal

0.96

 foods

0.95

Ingredients

0.94

Activations Density 1.954%

phrases related to food and nutrition

No Comments

No Known Activations