INDEX

Explanations

legal terms and phrases

oai_token-act-pair · gpt-3.5-turbo

legal terminology and phrases regarding liability and permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ï¸ı

-0.78

 Roose

-0.77

 Canaver

-0.76

ppa

-0.75

PDF

-0.75

think

-0.74

hack

-0.73

 gigs

-0.73

Sand

-0.72

 Collider

-0.71

POSITIVE LOGITS

 applicable

1.21

 practicable

1.17

 pursuant

1.14

 specified

1.12

 lawful

1.10

 licensee

1.10

'';

1.10

 thereto

1.09

 lawfully

1.08

 affirmative

1.06

Activations Density 0.834%

legal terms and phrases

legal terminology and phrases regarding liability and permissions

No Comments

No Known Activations