INDEX

Explanations

strings related to programming languages and code snippets

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

 constitu

-0.95

éĹĺ

-0.90

 Remem

-0.85

OIL

-0.84

Nun

-0.78

EStream

-0.78

å§«

-0.76

zai

-0.76

 suscept

-0.75

 unanim

-0.71

POSITIVE LOGITS

ynamic

1.57

iamond

1.46

etermin

1.37

elta

1.35

etermined

1.35

ividual

1.34

ynam

1.32

iscover

1.31

orm

1.31

ownt

1.29

Activations Density 7.553%

strings related to programming languages and code snippets

No Comments

No Known Activations