INDEX

Explanations

mentions of premium content, payments, and services

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

ADRA

-0.67

arming

-0.63

CLE

-0.61

ARB

-0.60

ãĤ¨ãĥ«

-0.60

prototype

-0.60

İĭ

-0.58

mable

-0.57

ãĤ±

-0.56

abad

-0.56

POSITIVE LOGITS

 premium

0.84

cedes

0.74

 fare

0.72

 upkeep

0.71

 premiums

0.71

 income

0.66

 billing

0.65

 grade

0.64

 footing

0.64

 tremend

0.64

Activations Density 8.215%

mentions of premium content, payments, and services

No Comments

No Known Activations