INDEX

Explanations

concerns or worries expressed in a text

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

ingers

-0.80

obs

-0.69

Bom

-0.68

 Carbuncle

-0.67

annis

-0.66

ortunately

-0.66

ingu

-0.65

artifacts

-0.65

oons

-0.65

obos

-0.64

POSITIVE LOGITS

wart

0.96

warts

0.90

 trolling

0.83

 Concern

0.78

 concern

0.78

lessly

0.76

 concerns

0.74

edly

0.72

 raised

0.70

 regarding

0.70

Activations Density 10.944%

concerns or worries expressed in a text

No Comments

No Known Activations