INDEX

Explanations

phrases related to memories or recollections, focusing on specific events or moments

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

osph

-0.53

ingen

-0.52

complex

-0.51

assi

-0.49

iken

-0.47

 juices

-0.47

olan

-0.46

phen

-0.46

asper

-0.46

atics

-0.46

POSITIVE LOGITS

 targ

0.55

 remotely

0.53

 sighting

0.53

irlf

0.52

âĢİ

0.52

 anybody

0.49

 Twice

0.46

:(

0.46

:,

0.46

Eag

0.46

Activations Density 9.194%

phrases related to memories or recollections, focusing on specific events or moments

No Comments

No Known Activations