INDEX

Explanations

causal relationships between different factors or variables

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

elight

-0.44

ucket

-0.40

HCR

-0.37

aeper

-0.37

atters

-0.37

leck

-0.37

attery

-0.36

guyen

-0.35

 interns

-0.35

lite

-0.35

POSITIVE LOGITS

ality

0.45

 attribut

0.45

 blindness

0.43

 attribution

0.39

Ca

0.37

aneous

0.36

WHY

0.36

 autism

0.36

why

0.36

 illness

0.35

Activations Density 10.446%

causal relationships between different factors or variables

No Comments

No Known Activations