INDEX

Explanations

instructions or steps in a recipe

oai_token-act-pair · gpt-3.5-turbo

cooking and preparation instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

emale

-0.73

iami

-0.68

href

-0.67

bourne

-0.63

 Labrador

-0.63

living

-0.62

DN

-0.61

andre

-0.58

humans

-0.58

years

-0.58

POSITIVE LOGITS

zzle

0.80

Ingredients

0.77

Assembly

0.76

 Ingredients

0.73

 excess

0.71

 mixture

0.69

azines

0.69

enz

0.68

Instruct

0.67

 Tables

0.66

Activations Density 0.099%

instructions or steps in a recipe

cooking and preparation instructions

No Comments

No Known Activations