INDEX

Explanations

information related to streaming services like Netflix and Amazon Prime

oai_token-act-pair · gpt-3.5-turbo

references to streaming services and their content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

afety

-0.91

phi

-0.89

 asphalt

-0.81

 embry

-0.77

Ada

-0.77

tal

-0.77

 grease

-0.76

 sprayed

-0.76

 Wildcats

-0.75

 muzzle

-0.75

POSITIVE LOGITS

 Netflix

2.32

Netflix

2.29

netflix

1.95

 streaming

1.86

 Hulu

1.83

flix

1.67

 Streaming

1.64

 Roku

1.56

HBO

1.39

 binge

1.30

Activations Density 0.248%

information related to streaming services like Netflix and Amazon Prime

references to streaming services and their content

No Comments

No Known Activations