INDEX

Explanations

product names and descriptions, possibly related to shopping and promotions

oai_token-act-pair · gpt-3.5-turbo

items related to food and beverages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 regress

-0.84

 privileged

-0.83

 intent

-0.83

 urgency

-0.82

 metabolites

-0.82

 vulnerabilities

-0.82

 outsiders

-0.82

 responsibility

-0.81

 culp

-0.81

 clauses

-0.81

POSITIVE LOGITS

 Balloon

1.46

 Wooden

1.40

 Bottle

1.39

 Plastic

1.39

 Brush

1.38

 Painting

1.36

 Wedding

1.35

 Poster

1.34

 Roller

1.32

 Hair

1.31

Activations Density 0.289%

product names and descriptions, possibly related to shopping and promotions

items related to food and beverages

No Comments

No Known Activations