INDEX

Explanations

statistical and demographic data

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

 acknow

-0.33

dp

-0.33

 crate

-0.30

lv

-0.30

wp

-0.30

hed

-0.29

 necks

-0.29

ecd

-0.28

 cabinet

-0.28

 WARN

-0.28

POSITIVE LOGITS

 Average

0.38

 Total

0.38

 Debt

0.38

letal

0.35

OTAL

0.34

 Tablet

0.34

ashtra

0.34

ificantly

0.33

 Population

0.33

renheit

0.32

Activations Density 7.614%

statistical and demographic data

No Comments

No Known Activations