INDEX

Explanations

number and unit combinations, such as measurements or dimensions

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

 breeding

-0.35

shire

-0.35

 eclipse

-0.35

 inhibited

-0.35

manship

-0.34

 instruments

-0.34

cano

-0.33

sag

-0.32

sonian

-0.32

 extinction

-0.31

POSITIVE LOGITS

clock

0.41

bleacher

0.39

ãĥīãĥ©ãĤ´ãĥ³

0.38

Occup

0.38

 Radius

0.38

Leary

0.38

Brien

0.38

0.37

Course

0.37

thumbnails

0.37

Activations Density 5.361%

number and unit combinations, such as measurements or dimensions

No Comments

No Known Activations