INDEX

Explanations

keywords related to specific ingredients used in cooking

oai_token-act-pair · gpt-3.5-turbo

mentions of ingredients in food or 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

zik

-0.78

graph

-0.64

III

-0.63

Dot

-0.62

lance

-0.62

ower

-0.61

Wide

-0.61

II

-0.60

Jub

-0.59

VI

-0.59

POSITIVE LOGITS

 ingredients

3.72

 ingredient

2.92

 ingred

2.36

 Ingredients

2.33

Ingredients

2.29

redients

2.11

 recipes

1.72

 additives

1.66

 spices

1.61

 herbs

1.53

Activations Density 0.016%

keywords related to specific ingredients used in cooking

mentions of ingredients in food or recipes

No Comments

No Known Activations