INDEX

Explanations

questions or statements in English language

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Configuration

neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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

sync

-0.85

pine

-0.82

 staple

-0.78

raper

-0.78

sonian

-0.78

fet

-0.76

simple

-0.74

 Include

-0.73

 Contains

-0.72

paste

-0.72

POSITIVE LOGITS

 regard

1.03

 Mons

0.97

 Emirates

0.91

 regards

0.88

pport

0.87

heit

0.87

 react

0.85

 relation

0.84

externalActionCode

0.83

 manifest

0.82

Activations Density 1.755%

questions or statements in English language

No Comments

No Known Activations