INDEX

Explanations

information related to IT systems, technology, and the practical application of programming languages

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 livest

-0.75

lished

-0.74

iewicz

-0.71

 Peninsula

-0.70

ideshow

-0.69

 contrace

-0.69

Osc

-0.68

artney

-0.67

 Parenthood

-0.67

phrine

-0.66

POSITIVE LOGITS

reading

1.31

reader

1.15

read

1.02

ificate

0.88

edly

0.87

ing

0.86

 proof

0.82

ingen

0.82

reads

0.81

 proofs

0.80

Activations Density 8.953%

information related to IT systems, technology, and the practical application of programming languages

No Comments

No Known Activations