INDEX

Explanations

Twitter handles preceded by '@'

oai_token-act-pair · gpt-3.5-turbo

social media handles and user interactions

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

EE

-0.81

Tol

-0.80

 Spac

-0.79

 Planes

-0.77

 aval

-0.77

 autop

-0.75

Tes

-0.74

 âĹı

-0.74

 pestic

-0.74

 Enchant

-0.74

POSITIVE LOGITS

John

1.73

 John

1.70

john

1.56

 JOHN

1.56

JOHN

1.56

 john

1.40

 Johns

1.39

 Johnston

1.34

Johnny

1.15

 Lennon

1.09

Activations Density 0.227%

Twitter handles preceded by '@'

social media handles and user interactions

No Comments

No Known Activations