INDEX

Explanations

phrases related to decision-making or people making decisions

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

ModLoader

-0.62

 Kern

-0.59

 Galile

-0.58

 coax

-0.57

bos

-0.55

 Burr

-0.55

 Nicarag

-0.55

 penn

-0.54

 pent

-0.53

||||

-0.53

POSITIVE LOGITS

based

1.05

related

0.99

wise

0.98

driven

0.97

seeking

0.95

oriented

0.94

specific

0.93

laden

0.91

sized

0.90

items

0.89

Activations Density 12.958%

phrases related to decision-making or people making decisions

No Comments

No Known Activations