INDEX

Explanations

terms related to legal matters and patent disputes

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt

Prompts (Dashboard)

12,288 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

46,080

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

apollo-research/Skylion007-openwebtext-tokenizer-gpt2

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

etheless

-0.82

 nursing

-0.81

 fasting

-0.72

 carbohyd

-0.69

imeters

-0.67

 suburbs

-0.64

 icing

-0.64

 breastfeeding

-0.61

 farmland

-0.61

 ferment

-0.61

POSITIVE LOGITS

Gate

0.99

 Opportun

0.96

Entry

0.91

 Direction

0.89

 Awareness

0.87

 Integrity

0.86

 Directory

0.86

 Therapy

0.86

 Definition

0.85

 Finder

0.85

Activations Density 13.363%

terms related to legal matters and patent disputes

No Comments

No Known Activations