INDEX

Explanations

legal or investigative terms

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

gren

-0.50

schild

-0.48

FUL

-0.48

fully

-0.47

glers

-0.45

stretched

-0.45

ful

-0.45

 Shelter

-0.44

oÄŁ

-0.43

 Machina

-0.43

POSITIVE LOGITS

iminary

0.86

 injunction

0.66

spection

0.59

udic

0.58

 examination

0.58

tenance

0.54

 examinations

0.51

agonist

0.50

isal

0.49

 investigation

0.48

Activations Density 8.448%

legal or investigative terms

No Comments

No Known Activations