INDEX

Explanations

phrases related to various aspects of eating

oai_token-act-pair · gpt-3.5-turbo

references to the act of eating

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

PV

-0.73

Beck

-0.71

 Archangel

-0.71

fitted

-0.68

å§«

-0.66

Aus

-0.66

 Aerospace

-0.66

RL

-0.66

âĹı

-0.65

 Stur

-0.64

POSITIVE LOGITS

 habits

1.14

 carbohyd

1.03

oleon

1.02

 eating

1.02

 eaten

1.01

 foods

0.98

 meals

0.97

eat

0.94

uana

0.93

 disorders

0.93

Activations Density 0.012%

phrases related to various aspects of eating

references to the act of eating

No Comments

No Known Activations