INDEX

Explanations

legal terms and actions related to authorization and permits

oai_token-act-pair · gpt-3.5-turbo

terms related to legal authorization and governmental processes

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

fact

-0.77

enth

-0.75

luck

-0.71

fortune

-0.70

fam

-0.68

answered

-0.68

 countered

-0.68

 partName

-0.67

wake

-0.67

issues

-0.67

POSITIVE LOGITS

 issuance

1.03

use

1.02

 sale

0.90

 indefinite

0.86

 manufacture

0.81

 unrestricted

0.80

 deployment

0.79

 cultivation

0.78

 operation

0.78

 leasing

0.78

Activations Density 0.193%

legal terms and actions related to authorization and permits

terms related to legal authorization and governmental processes

No Comments

No Known Activations