INDEX

Explanations

ingredients in recipes

oai_token-act-pair · gpt-3.5-turbo

mentions of ingredients used in recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

thood

-0.75

roe

-0.71

arton

-0.71

 Limbaugh

-0.70

udeb

-0.69

iscopal

-0.69

oj

-0.67

 Stellar

-0.66

Seg

-0.65

 Chatt

-0.65

POSITIVE LOGITS

 ingredients

1.17

 ingredient

1.04

Ingredients

0.97

 ingred

0.82

 suppliers

0.81

 additives

0.76

 supplier

0.73

cream

0.73

 thereof

0.73

odium

0.73

Activations Density 0.013%

ingredients in recipes

mentions of ingredients used in recipes

No Comments

No Known Activations