INDEX

Explanations

ingredients and cooking instructions

oai_token-act-pair · gpt-3.5-turbo

terms related to food ingredients and their effects

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

 adjourn

-0.70

DEM

-0.70

auld

-0.69

 Commons

-0.68

 timetable

-0.66

LM

-0.63

uploads

-0.63

 Camer

-0.61

 Lords

-0.61

quest

-0.61

POSITIVE LOGITS

 oxide

1.10

 additives

1.08

 potassium

1.07

oxide

1.02

 salts

1.00

 acidic

0.98

 phosphate

0.97

 coating

0.95

 soluble

0.94

 arsenic

0.93

Activations Density 0.241%

ingredients and cooking instructions

terms related to food ingredients and their effects

No Comments

No Known Activations