INDEX

Explanations

information related to historical events and characters

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

ially

-0.37

lash

-0.34

":"/

-0.34

 correction

-0.34

atively

-0.33

ħ

-0.32

ens

-0.32

heartedly

-0.32

DATA

-0.31

onse

-0.31

POSITIVE LOGITS

 respectively

0.58

 which

0.52

aka

0.48

 wherein

0.46

 namely

0.45

 whose

0.45

 culminating

0.42

which

0.41

whose

0.41

who

0.41

Activations Density 9.173%

information related to historical events and characters

No Comments

No Known Activations